Changelog: Bug fixes & improvements

Scholarly is always improving. Here you can find every bug fix, major feature, and other improvements we've made.

September 5th, 2026

Schedule a Laureate downgrade

Billing settings now let Laureate subscribers switch to Premium at the next renewal, review the price and date, and undo the change before it starts. Premium has no lower paid plan option.
Support staff can now review, schedule, and undo a Laureate-to-Premium downgrade from the admin user page. Changes take effect at renewal.

Uploaded files keep their names

Uploaded documents and audio no longer receive automatic AI titles during processing. Library files also preserve spaces and non-English characters in their filenames. You can still rename files yourself, including long uploaded recording names without cutting them short. Format conversions may update the extension of the processed copy.

September 4th, 2026

Large uploads and recording recovery

Laureate uploads can use the full 1,000 MB allowance. Oversized requests now return a clear size error instead of repeatedly retrying as a connection failure.
Recording pages distinguish a temporary loading error from a missing recording and offer a retry button. When transcription finds no speech, the message asks you to check the saved audio before retrying or changing your microphone.

Preserving work during AI recovery

Video retries keep their recovery model, and long chat turns can continue beyond 50 tool rounds. Flashcard decks retain completed cards when some source sections still fail after retrying, with a visible warning that coverage may be incomplete.

Project chat starts without a layout flicker

When you send a new project-scoped chat, the project picker now disappears as soon as sending begins, in step with the composer moving from the center to the bottom of the conversation.

Clearer reasons for rejected uploads

Starting a transcription with an empty or unsupported file now shows the specific reason, such as the file being empty, instead of an unexplained failure.

September 3rd, 2026

Scholarly works for every kind of learner and creator

Chat and AI creation now address you as a user or learner instead of assuming everyone is a student. The underlying guidance also covers professional and personal work alongside studying.

Kimi K3 and Muse Spark 1.3 join Recommended Models

Moonshot AI's Kimi K3 and Meta's Muse Spark 1.3 are now Recommended across Chat and every AI creation tool. Both can reason over images and long source material, and their official provider logos appear throughout the model picker.
Kimi K3 and Claude Sonnet 5 use 2 AI creation credits, with a 2× badge shown before selection. Muse Spark 1.3 uses 1. Chat remains unlimited on paid plans and never consumes creation credits.

Image-ready GLM 5.3 Flash across Chat and AI creation

Z.ai's multimodal GLM 5.3 Flash replaces Deepseek Flash in Chat, Deep Research, Slides and documents, Video Lectures, Infographics and Mind Maps, Flashcards, Podcasts, and Customization Profiles. It can read images and video as well as text, and saved Deepseek Flash choices move to GLM automatically.

Combine more sources in one creation

Every creation tool now shares one source limit that grows with your plan: 10 sources per creation on Premium and 20 on Laureate (and their Teams equivalents), up from a flat 3 everywhere; Free creations use one source, matching the single Free upload. Flashcards, quizzes, podcasts, video lectures, slides, study guides, infographics, mind maps, worksheets, spreadsheets, essays, story books, timelines, and Deep Research all use the same number, and the add-source picker now says exactly which plan lifts the cap instead of only asking you to remove a file.

Personal Laureate returns to monthly billing

New Personal Laureate subscriptions are now monthly only. The short-lived $950 yearly option has been removed; Premium and both Teams plans keep their existing monthly and yearly choices.

Checkout confirmation and your chosen plan survive sign-up

If you still need to finish your name or usage step after checkout, Scholarly now keeps the purchase confirmation and the plan you picked on Pricing instead of sending you back to an empty sign-up page.

Uploads and paid creation recover cleanly

Password-protected PDFs can now be unlocked and uploaded without repeating the same password error. Dropped image, video-link, and recording requests retry safely without duplicate uploads; Video Lectures recover once from a hard generation timeout before refunding. Scholarly also catches multi-audio selections before upload, replaces cryptic numeric errors with useful guidance, and retries brief Stripe outages while preparing a Laureate upgrade.

Question banks, Video Lectures, and sign-up keep more of your work

Flashcard decks that preserve every source question now retry any section that came back empty before deciding the deck. A single blank section no longer discards the rest of a finished bank.
Video Lectures accept a narration script that runs slightly past the requested length instead of asking for rewrites until the lecture fails. Only a script well over the ceiling is sent back, and only once.
Signing in with Google One Tap from a marketing page while tapping Get started now lands new accounts in onboarding, not straight on Home.
When our YouTube transcript provider is out of capacity, video imports now say so and let you retry later instead of reporting a rate limit that would clear in a minute.
Your task list and in-progress creations no longer drop out with a temporary connection error while internal reporting runs. Heavy admin reports are now bounded so they cannot crowd out the requests the product itself is making.

September 2nd, 2026

Home and recording handoffs feel faster

Returning accounts can start creating as soon as their own workspace content is ready, without waiting for optional shared and recent sections. Finishing a recording also hands the saved audio to transcription immediately instead of waiting on a separate duration check; the transcript still supplies the final duration.

Premium offers now start with yearly savings

Premium plan screens now start on yearly billing across the product. Monthly billing remains available in one click, and a billing period you already selected on Pricing is always preserved.

Pricing keeps your plan choice through sign up

Choosing Premium or Laureate on Pricing now carries the selected plan and billing period through sign up, sign in, Google authentication, and onboarding. It also works before the page finishes loading and when the button is opened in a new tab, so the requested plan screen is never lost.

Gemini 3.8 Flash across Chat and AI creation

Google's new Gemini 3.8 Flash replaces Gemini 3.7 Flash in Scholarly's paid model catalog. Saved 3.7 Flash selections carry forward to 3.8 Flash automatically, while Claude Sonnet 5 and Claude Opus 5 remain available.
Flashcard Auto uses Gemini 3.8 Flash at low reasoning on Premium and medium reasoning on Laureate; Free routing is unchanged. Paid Video Lecture Auto uses GPT 5.6 Luna with a higher reasoning budget, while Claude Sonnet 5 remains available to choose.
Gemini 3.8 Flash is a standard one-credit creation model. GPT 5.6 Sol and Claude Opus 5 remain the 3-credit Frontier options.

Every creation modal now saves into a project

The Upload, Flashcards, Quiz, Video lecture, Podcast, and Deep Research modals now show a “Saving to” chip in their header. It defaults to the project you used most recently, and you can switch projects, choose No project, or create a new project inline without leaving the modal. Sources and finished artifacts land in that project together.

Home chat starts inside your latest project

The Home composer now defaults to your most recently used project, so a question from Home is answered from that project’s sources instead of an unscoped chat. Pick No project to keep global chat, and Home remembers your choice.

Bug fixes

Video lectures, AI Slides, and AI Documents no longer fail on the first attempt when our processing environment refuses to start a workspace. They wait and retry automatically, and only report a failure once those retries are exhausted.
Deleting your account now signs you out and confirms right away while the data removal finishes in the background. Previously the request stayed open for a minute or more and could show “Your account could not be deleted” for a deletion that was succeeding. If the background handoff is interrupted, Scholarly now resumes it automatically; while removal is still running, a new sign-in or same-email registration waits instead of reopening the account.
Signing up with Google One Tap from a marketing page could land on Home and skip onboarding. New accounts are now taken to onboarding even when another navigation wins that first moment.
Hovering a link to a stored file inside a page now shows the file name instead of a “Couldn’t read that link” error.

September 1st, 2026

AI Slides and podcast slides get the video lecture's visual toolkit

AI Slides now build from a typed vocabulary of slide kinds — title, key idea, definition, bullets, comparison, process, diagram, stat, equation, chart, table, timeline, quote, callout, image, and closing — each with its own layout, and draw relationship diagrams, process flows, timelines, charts, equations, and icons from the same palette-aware kit the Standard video lectures use. Decks are planned before they are written, checked for overflow and honest slide kinds before rendering, and reviewed on readable contact sheets before delivery.
Podcast companion slides now choose the shape that fits each chapter — key points, a comparison, a step-by-step process, a headline statistic, a definition, or a timeline — instead of always listing bullets, follow the episode's chosen look and Dark Mode, and get a second pass when a chapter's copy would not fit the slide.

Colour looks and Dark Mode for AI Slides and podcast slides

The colour variants and Dark Mode that video lectures gained last month now cover every slide creator. AI Slides and the podcast visual companion draw a fresh colour look for each generation — the same set of paper tones and accents Standard video lectures use — and a new "More options" panel in each create modal lets you pick a specific look or switch the slides to a dark theme. Existing decks and podcasts are unchanged; the classic cream look remains the most common draw.

Team setup is faster and gives admins control from the start

New teams now move through one clear setup flow: name the workspace, choose which model groups members can use, invite teammates, set the seat count, and then choose a plan. Team data loads before each screen appears, invite links and form choices stay in place when moving between steps, and model access can still be changed later from Team settings.

The Team page now has a full navigation bar

Team sections are now real pages — Overview, People, Profiles, Settings, and Billing — with icon navigation under the header. Invites live on People, model access and customization live on Settings, and plans, seats, payment controls, invoices, and receipts are together on Billing.

Upgrade prompts now explain what Premium changes

When a Premium feature blocks an action, the plan screen now keeps that exact goal in view: longer podcasts, better AI models for videos, flashcards, podcasts, chat and AI PDFs, more PDF coverage, or unlimited exam retakes. The prompt explains the concrete improvement before showing the plans.

Finishing a recording no longer loses the audio

When a recording finished, Scholarly measured its length before saving it — and if that measurement service was briefly unreachable, the finished capture was discarded and the recording was marked failed even though the audio had uploaded cleanly. The length is now optional: the recording is kept and processed, and its duration is filled in from the transcript a moment later.

Waiting on a YouTube transcript reads as a wait

Asking for a transcript while YouTube is still generating one is a normal wait you can retry, and it is now reported that way instead of being recorded as a failure.

New uploads reach the right follow-up email

If an email tried to use a newly uploaded file before its text was ready, Scholarly could send the plain fallback immediately. It now waits for the source to finish so the email can include relevant study-content suggestions; files without usable text still receive the plain version.

Your source and your artifact survive a provider outage

Adding a YouTube video no longer fails when the transcript service itself is down, rate-limited, or slow — the video is added straight away and its transcript is fetched from the video page, the same way a transcript that is still generating already worked. Videos with no captions, deleted videos, and live streams still tell you to pick a different link.

A finished infographic is never thrown away over a search-indexing hiccup

Infographics and mind maps used to be deleted, and the whole request marked failed, if the step that indexes the finished PDF for search and citations hit an outage. The artifact is now delivered as soon as it is rendered, and indexing retries quietly in the background.

Empty files are caught before you wait on an upload

Picking a 0-byte file — an iCloud or Drive placeholder that has not downloaded, a recording that never finished writing — now says so immediately in every create flow, instead of uploading it and returning an error you could not act on.

August 31st, 2026

Premium pricing now feels local in more countries

Premium now shows and charges matching local prices in Japan, Saudi Arabia, Switzerland, New Zealand, the United Arab Emirates, South Korea, Hong Kong, Israel, Nepal, Argentina, Colombia, and Zambia. Every existing localized price remains unchanged, and monthly subscribers still receive the same yearly savings offer.

Laureate and Teams now support local currencies

Laureate now shows and charges the equivalent amount in supported local currencies, while Premium Teams and Laureate Teams add the same local-currency support at checkout without changing their global USD price. Personal Laureate also adds a $950 yearly option, saving about 20% compared with twelve monthly payments.

AI output follows your language everywhere

With the AI language set to Automatic, podcasts, mind maps, AI documents, essays, narrations, and research reports now follow your source material's language instead of defaulting to English.
Exam feedback, generated PDF titles, folder organization suggestions, and text inside chat-generated images now match your language too.
Read-aloud now speaks Japanese documents with a natural Japanese voice.

Emails in your language

Every email Scholarly sends — creation-ready notices, sign-in and password emails, billing, renewals, team invites, and referrals — now arrives in Japanese when your app language is Japanese.
Emails always arrive: anything not yet translated is delivered in English instead of failing.

Uploads and upgrade buttons work after the page loads

Fixed a translation-context error that could stop an uploaded source from reaching the next creation step or make an upgrade button do nothing. Sign-in data and pinned chats now use the same safe translation context, while keeping your selected interface language.

Chat remembers the rest of your conversation again

The context budget for a chat turn had been outgrown by the instructions and workspace context Scholarly sends with every message, leaving almost nothing for the conversation itself — so on most turns the assistant was handed only your newest message and the reply just before it, and earlier turns were dropped. A twelve-exchange conversation reached the model as three messages. The budget now leaves real room for history, so follow-up questions, corrections, and anything you established earlier in the thread stay in view.

AI generations recover from a provider safety stop instead of failing

When a model provider's safety filter stopped a generation part-way through, the run ended permanently on the first attempt with no second model tried — a slide deck could lose several minutes of work that way, and the recovery pass that could have saved it stopped for the same reason. A safety stop is now recognised for what it is and the work is handed to a different provider, which is what every other provider already did.

Search stays fast and precise after a deployment

If a search landed in the short window during a deployment while a search index was still being rebuilt, that server permanently fell back to a slower, less precise way of matching — for everyone it served, until it restarted. It now re-checks shortly afterwards and returns to the fast, relevance-ranked path as soon as the index is ready.

Full page titles and cleaner Japanese messages

Marketing page titles no longer cut off at the “|” separator — the full title, including the Scholarly brand, shows in the browser tab and search results again.
Japanese creation alerts now name the artifact you actually made — generating a mind map or infographic no longer reports that your PDF is ready.
When a pasted link can't be read, the message includes the specific reason again instead of only generic guidance.

August 30th, 2026

Deep Research is clearer while you work

Deep Research now uses the same light-bulb icon in the sidebar as research reports throughout your library.
The Thinking status now animates its ellipsis so it is visibly active while Scholarly prepares your research.
Research started inside a Project keeps that Project in the breadcrumb while the report is still running, instead of showing only the report title until completion.
Deep Research now creates one polished PDF for the cited report by default, without duplicating the same report as DOCX and Markdown files. Distinct files are still created when you request them.

Research is now a primary Team workspace action

Team members can start Deep Research directly from Home's four main creation buttons. Flashcards remain available in the creation row below, while personal workspaces keep their existing Home layout.

Signup buttons work reliably across every marketing page

Free, Premium, Laureate, tool, feature, and Japanese signup buttons now use real registration links that work before the page finishes loading, with JavaScript disabled, and when opening a new tab. This fixes clicks that could leave visitors on the same page or return them to Pricing.

Shared links open for people who aren't signed in

A shared research report sent to someone without a Scholarly account could bounce them straight to the login screen instead of showing the report. Signed-out visitors now land on the shared work itself, with Copy link and Sign up available, and every public share page is protected from the same eviction.

Video lectures recover instead of failing outright

A lecture could be handed to a model we had retired from video — as the automatic recovery pick after an ordinary provider hiccup — and that model had no backup of its own, so the next hiccup ended the whole generation. Retired models are no longer offered as recovery on a surface they were withdrawn from, requests still pinned to one move to your plan's current video model, and both keep their normal retry and provider-fallback safety net.

Settings text reads clearly in dark mode

Headings and amounts in Billing history, weekly creation usage, and the cancellation screens were rendered in a muted grey that read as disabled against the dark surface. They now use full-contrast text, so the plan totals and invoice amounts you are checking are the easiest things on the page to read.

Japanese now reaches Library, Projects, and Chat

Choose Japanese in Appearance to use the Library and folders, Projects and their workspaces, the main Chat experience, feedback prompts, and the cancellation flow in Japanese. Names, source content, and AI answers stay in their original language, while the controls and guidance around them follow your app language.

Creation tools now stay in Japanese

After you choose a tool on Home, the complete source-to-create flow now follows your app language for Flashcards, Quiz, AI documents, Slides, Podcasts, Text to Speech, Transcription, Study Guides, Study Packs, Video Lectures, and Deep Research. Upload, Library and Google Drive selection, page ranges, prompts, schedules, model, voice, and design controls, warnings, and final settings are translated. Japanese labels do not change source names, provider content, or the language you asked AI to generate.

The rest of the signed-in app now speaks Japanese

Japanese now covers sign-up and account recovery, Teams and sharing, study modes and exams, editors and exports, recordings, podcasts, video, Research, previews, billing and upgrade states, background task progress, and errors. Signed-in URLs stay unchanged, and switching the interface language does not change file names, source content, or the language you asked AI to generate.

August 29th, 2026

Research ends in files, not a wall of text

Deep Research is rebuilt as a professional workspace with its own sidebar destination. Scope a run to a Project, attach internal sources, choose the evidence mix, depth, model, and deliverables, or start from workflows for literature review, market landscape, policy analysis, and due diligence. Finished work opens with a concise verdict, confidence and contested-claim signals, and open questions. Read the complete cited report in its own Research tab, inspect sources in Evidence, and preview generated briefs, tables, charts, and working data in a full-screen file workspace without leaving the session. A dedicated chat stays beside the research and already knows its reports, findings, and sources.

Core dashboard flows are now available in Japanese

Choose Japanese in Appearance to use Japanese on Login and Home, in app navigation and the Home creation menu, across Connections, and in the main account, preference, support, billing, invoice, and usage settings. Shared AI language and voice controls are translated too. Application URLs stay clean, such as /home, /connections, and /settings, while /jp remains reserved for translated public pages.

Counts, allowances, and model labels say exactly what they mean

Add Content now shows the upload slots your plan actually has left while keeping Library and Drive available. Home's Content count includes work that is visibly processing or ready to open, Free's automatic model is labelled Auto (Free), lifetime Billing allowances no longer imply a daily reset, and Podcast Deep dive badges count the notes actually shown. We also removed the outdated Short Videos 'New' badge and rewrote limit banners around the next action you can take.

Clearer Explore matches and calmer study feedback

Explore no longer mixes unrelated recent work into search results. When a result matches inside a page or PDF instead of its title, the card shows the matching source excerpt, and older titles with broken character encoding are repaired before display. True-or-false quiz prompts stay behind the quiz instead of appearing as answers on the flashcard front, exam feedback no longer adds reaction emoji after mistakes, and Chat's exact-source rules now explicitly protect adjacent repeated digits in multilingual identifiers.

Stronger automatic direction for paid Video Lectures

Video Lecture Auto now uses Claude Sonnet 5 with low reasoning for Premium and Laureate. Free lectures keep their existing model, and choosing a model yourself still uses exactly the model you selected.

AI chat is easier to read

Chat replies now use a lighter body weight, so longer answers are easier to scan. Headings, bold, and other emphasis stay as they were.

Chat answers instead of retrying a workspace that won't start

If the file workspace behind chat cannot start, the assistant now says so once and answers with everything else it has. Previously it kept retrying the same step in a loop, which made a short outage look like a stalled reply.

Study guides and slides survive a network blip

Loading your sources into the generator no longer fails the whole document when the connection stutters for a moment. The step now retries on its own, so a passing hiccup stops costing you a finished study guide, slide deck, or other generated document.

Clearer text and fuller teaching in AI Video Lectures

Illustrated lectures now add labels after the artwork is generated, keeping instructional text exact instead of relying on an image model to spell it. Standard lectures also check every requested topic individually and keep longer explanations moving through more meaningful visual beats.

August 28th, 2026

Chat can set up a project for you

When a conversation turns into ongoing work, chat now offers to give it a project — and can create one and move the chat into it, so every artifact it produces from then on is filed there. It can also find your projects and past chats by name, look inside one project, and rename, file, or put away your pages, files, folders, and projects on request.
Chat can now build something for a time you name. Say your exam is Friday or that you go through a report every Monday, and it will offer to have the study guide, deck, or summary waiting for you then. Scheduled work appears on Home, where you can run it sooner.
Chat answers are shorter and lead with the answer, with less preamble, fewer unnecessary headings, and no closing recap.

A cleaner way to start project chats

Creating a project from the chat picker now asks for its name before creating and selecting it. Once a conversation has started, the extra project picker disappears because the chat's project is already shown in the breadcrumb. Form fields also keep the same quiet surface when focused instead of growing a border, ring, shadow, or scale effect.

Chat with a project from anywhere

The chat box on Home and in full-screen Chat now has a project picker. Choose a project and your next question is grounded in that project's sources, without opening the project first. A chat you have already started moves with you when you pick a project, switching projects is one click, and project chats now run full width on the same Chat screen as everything else: the project page has a new expand button that takes the conversation there.

Search finds every chat, not just global ones

Command palette search (Cmd/Ctrl+K) now returns your project chats and the conversations you have held over a PDF, page, recording, podcast, video, folder, or file, matching on what was actually said in them rather than titles alone. Each result is labelled with the kind of chat it is and opens in the right place.

A clearer Home for every AI creation

Home now uses larger, explicit names for its core tools, keeps Start Recording in the main row, and moves Text-to-Speech and Transcribe into More tools. AI Mind Map, Worksheet, and AI Infographic are now document types inside AI Document Creator, so one source-and-customize flow covers them alongside reports, timelines, spreadsheets, and other files.

Dashboard language without a different URL

Changing the dashboard language now keeps you on the same clean application address, such as /home or /chat. Locale-prefixed addresses are reserved for translated public pages.

Connect only the Drive files you choose

Google Drive now has its own Connections page with per-account approval, default, reconnect, and disconnect controls. One Drive connection covers only files selected through Google's Picker, including Docs and Slides; Chat can search and read them but cannot browse the rest of Drive or edit your files.

Chat holds on to your files through a network blip

When chat stages one of your files into its workspace, a brief network hiccup no longer ends the attempt. The step now waits out a short outage instead of giving up in under a second and asking the assistant to start over, so a passing blip costs you a moment rather than a stalled reply.

Finished study guides are recorded as finished

A PDF study guide that finished generating is now always recorded as complete, even if its underlying record changed mid-run. Previously that timing could leave a finished study guide showing as still working or failed.

Emails about a new upload wait for the file to be read

When you upload a PDF, the follow-up email about it now waits until the file has finished being read before it is prepared. Emails that used to arrive without the questions and key points from your document now carry them.

A clearer answer when Office hands over its lock file

Uploading one of the hidden "~$" files Microsoft Office keeps beside an open document now says exactly that, instead of suggesting your document is corrupted or password-protected.

Settings, billing history, and shared projects hold up in more cases

Invoices and receipts no longer disappear when a single billing document link comes back in an unexpected format — the history now loads and drops only the affected link. Billing history shows a spinner while it loads instead of grey placeholder rows that resized the page when the data arrived. A shared project's collaborator list keeps rendering when an access request has no readable email address. And a settings address with no page behind it no longer opens an empty panel.

August 27th, 2026

Explore now gives every kind of work its own stage

Explore has been rebuilt as one coherent public library without flattening everything into the same card. Short Videos are vertical, Podcasts have episode artwork and waveforms, Flashcards show a real question, Research shows its abstract and sources, and generated presentations, study guides, and pages each have a format-specific design. Every discoverable Explore category is now available in English and Japanese with crawlable content, structured data, clearer search, and complete sitemap coverage. Privacy-sensitive workspace formats such as meeting notes and folders stay out of discovery.

Practice and generated decks preserve the lesson

Practice no longer drops signed numbers or percentages from true-or-false statements before grading them. Generated Slides recover multilingual text and punctuation instead of showing encoding garbage, and Video Lecture companion PDFs now include searchable, selectable text for assistive technology.

Keyboard-safe Settings and team-specific pricing

Keyboard focus now stays inside Settings until it closes, and the rest of the app is unavailable to assistive technology while the dialog is open. On Pricing, switching to Business now also changes the comparison to Premium for Teams and Laureate for Teams, including per-member allowances, workspace access, shared libraries, and central billing.

Shared projects are now real workspaces

People you invite—and teammates with access—can now open shared projects from their own Projects list, chat across the shared sources, edit the shared brief and instructions, see the other active collaborators, and keep their own Private Chats and Private Memories. Only the owner can add or remove project content, manage members, change the default profile, or archive the project.

A guided team setup that starts with your people

Creating a team now walks through four clear steps: name your team, invite teammates, pick a plan, then choose seats. The first step introduces Scholarly through podcasts, video explainers, and answers grounded in your material, plus sharing sources and finished work with your team. The invite step offers both email invites and a shareable join link. Seats are pre-filled to cover everyone you invited, and invites beyond the trial capacity are sent automatically the moment your plan activates.

Team trials now include seats for teammates

A free team trial includes 3 seats, so you can invite teammates by email or join link before paying anything. Everyone keeps the limits of their own plan during the trial, and upgrading covers every member from one invoice.

Leave a team yourself

Members and admins can now leave a team from the Team page's Overview tab — no need to ask an admin to remove you. Leaving frees your seat and immediately lets you accept an invite to a different team.

Roomier settings and billing documents

Settings stays in its familiar window, now with more room and grouped Account, Workspace, AI, Billing, and Support sections. Billing now includes downloadable invoice PDFs and Stripe receipts for personal purchases, plus team billing documents for workspace owners and admins.

Shared projects include all content, not chats

Sharing a project now gives invited people and teammates a read-only view of everything in it — files, pages, folders, and the items inside those folders. Nested content opens from the shared project the same way it does for you. Project chats stay private and are never shared.

Undo and redo in the flashcard editor

The flashcard editor now has visible Undo and Redo controls, plus Cmd/Ctrl+Z and Cmd/Ctrl+Shift+Z shortcuts. Changes to card text, order, images, generated additions, repairs, and added or deleted cards can be reversed, and the restored deck saves automatically.

Audio and video play inside in-app browsers

Podcasts, AI Meeting Notes recordings, voice previews and video playback now start correctly when Scholarly is opened from a link inside another app. Pressing play there previously did nothing.

Chat waits for a long YouTube transcript instead of failing

Asking about a YouTube video whose transcript is still being generated now tells you it is still processing and to ask again shortly. The question used to fail outright with a message suggesting the video was unavailable.

Seeking a paused recording moves the player right away

Jumping to a topic or a line of the transcript while a recording is paused now moves the progress bar and highlights the right topic immediately, instead of appearing stuck on the old position until you press play again.

Upgrade prompts no longer show a leftover error

When a creation hits your plan's AI limit, the AI Document, Essay, and Spreadsheet creators now clear any earlier error message before showing the upgrade options, so the reason you are being asked to upgrade is the only thing on screen.

August 26th, 2026

Transcribe audio, video, and YouTube into a file

The new Transcribe creator turns up to 60 minutes of audio, video, or a YouTube video into either a clean .txt file or timestamped .vtt captions. Each transcription uses one AI credit for the whole source, runs in the background, and returns the credit automatically if it fails. The narration feature is now named Text-to-Speech everywhere.

Choose your app and AI languages separately

Appearance now includes an App language control for Scholarly's interface. The existing output-language control is now clearly named AI Language under Chat, so changing menus and navigation never changes the language used for AI responses or new creations.

Flashcard decks repair themselves before Practice

Duplicate or missing internal card identifiers are now repaired automatically whenever a deck is edited or opened for Practice or Exams. A damaged deck no longer fails while preparing study questions.

Organize your library from project chat

Project chat can now manage your workspace for you: ask it to rename, archive, restore, or move pages, files, and folders, or to create a new folder, and it happens right from the conversation. Archiving is always reversible, and everything the chat creates is filed into your project automatically — even if you close the tab before it finishes.

Approve AI edits to your pages, decks, and files

You can now ask project chat to rewrite a page, update a flashcard deck, or edit a file anywhere in your project. Every edit arrives as an approval card in the chat — review the summary, then accept to apply it or deny to dismiss it. Nothing changes until you accept, and the card keeps working even if you come back to it later.

Returning context chats stay focused

When a project, PDF, video, page, folder, or other content already has conversations, its sidebar now leads with those recent chats instead of repeating the full Chat introduction. New contexts still explain what Chat can see, and quick starter questions remain available.

The upload limit is answered before you start recording

Free accounts that have used their upload now see the plan window when they start AI Meeting Notes, instead of recording a full session and being turned away at Finish. A recording that has already captured audio always finishes, even if the allowance ran out while it was running.

Running out of quiz questions offers a way forward

When the free quiz allowance runs out mid-session, Scholarly now opens the plan window instead of showing a warning that disappears while answers keep going unsaved.

Long YouTube videos are added right away

A YouTube video whose transcript is still being generated is now added to your library immediately, and the transcript finishes on the video's own page. It no longer fails after a two-minute wait and asks you to paste the link again.

Pasted text keeps its colours

Text pasted from a web page or document keeps the colours it came with. They were previously dropped whenever they arrived in a CSS format rather than a hex code.

Previewing a second PDF shows the right document

Opening one PDF preview and then another now shows the second document. Previously the preview kept displaying the first PDF until the page was reloaded.

Office files import whatever the file is named

A Word, PowerPoint or Excel file whose name carries stray spacing now imports normally instead of being rejected as an unsupported format.

Research asks what to produce

Deep Research no longer requires an extra file before you start. After you describe the objective, it asks what you want back — a cited report, slides, a brief, a study guide, a table, or something else — and you can pick more than one option or type your own.

August 25th, 2026

Email sign-in links send again

Requesting a sign-in link from the “Email sign-in link” page failed with an “Email is required” error even when the email address was valid. Sign-in links now send correctly.

Home stays focused on what you create

Weekly Brief has been removed from Home. Scholarly no longer creates or emails automatic briefs from recent material, so Home stays focused on the projects, content, and creations you chose.

The weekly creation wall no longer leads with a bill

When Premium's 10 weekly AI creations are used up, the first button is now Keep creating — 80 this week, and credit packs stay as a secondary option. The prorated amount due today and 20% off the next two full Laureate months appear after you open the plan window, not on the wall itself.

Every sidebar chat offers a useful place to start

When you open Chat beside a PDF, video, flashcard deck, page, project, file, podcast, recording, folder or research report, a fresh conversation now offers three questions tailored to that content. Choose one to ask it immediately, or write your own message as usual.

Practice and generated content stay faithful to your sources

Older true-or-false questions that repeated a flashcard correctly but were saved with the wrong answer key are repaired before Practice or Exams use them. Chat, Slides and Video Lectures also preserve multilingual identifiers, signs, percentages, decimal precision and scientific notation from the source instead of normalising or borrowing details from a neighbouring value.

Background creations finish and recover cleanly

Completed Slides no longer disappear when their background-task mirror arrives late. Story Books can use your Custom Designs on every plan as intended, YouTube summaries can be retried while captions are still processing, and Flashcards guide you back to replace an image source that is no longer available.

Better Slides layouts and truthful Podcast details

Generated Slides now use the full canvas more consistently, keep tables in readable rows and columns, and retain each slide's own styling in the final PDF. Podcast pages show the speakers and voices actually present in the transcript, including solo and larger casts. Short Video is now described simply as a short video format rather than a fixed-length promise.

Clearer source limits and safer table pasting

The Add content window now shows when all three source slots are full, disables every additional picker consistently, and tells you to remove a source before adding another. Pasting part of a table into the page editor also handles row-spanning cells without crashing the editor.

Projects, reports and files open instantly when you come back

Returning to a project, a research report, a recording or a file no longer rebuilds it from scratch. Each one now reopens with what it already had on screen instead of clearing to a loading spinner and fetching the same content again, so moving between two projects is immediate after the first visit. Reload the page whenever you want to pull in changes made elsewhere.

Opening a research report no longer flashes “not found”

Opening a research report directly by its link briefly showed “Research session not found” before the report appeared. The page now shows a loading indicator until the report is actually there. Shared conversations and the Explore category pages had the same kind of flash and have been fixed too.

Finishing a recording that was already processed no longer reports a failure

If a recording had already been finished — in another tab, or by an earlier click whose response you never saw — pressing Finish again answered "Recording cannot be completed in its current state" and the capture bar kept offering a button that could only fail. Scholarly now recognises a recording that is already processing or ready, takes you to it, and stops a capture that outlived it with a clear message instead of a connection warning.

The AI Video Lecture preview shows its cover image again

The sample lecture shown before you upgrade was loading without a cover frame. Its preview image now appears as intended.

August 24th, 2026

Connections: your Google Drive files in Chat

Connections now has its own place in the sidebar. Link more than one Google account and Chat can search and read the Drive files you share with Scholarly — grounded answers straight from your own documents. Access is read-only and per-file: Scholarly sees only what you share through the Drive picker and can never change or delete anything. Each account is managed independently, with one set as the default for Chat.

Scheduled tasks start at the local time you asked for

When you asked Chat to schedule something at a time such as “2 AM my time,” it could guess a different time zone and start hours early or late. Chat now uses your current time zone for relative and unqualified times. Future tasks are also labelled Scheduled everywhere they appear, and cannot be picked as sources until they have finished.

Chat recovers when an AI provider disconnects before answering

If Grok or another AI provider closes a response before any answer reaches you, Chat now moves to a compatible backup model automatically instead of ending with a generic error. If part of the answer or an action has already started, Chat still stops safely and lets you retry rather than mixing two models or repeating an action.

Deleting your account no longer looks like it failed

When a deletion took longer than the page waited for, Scholarly showed "Failed to delete account" and every retry answered the same way — even though the deletion was running and finished moments later. Deleting your account now recognises a deletion already in progress and signs you out normally instead of reporting a failure.

Removed YouTube videos are named for what they are

Adding or asking about a YouTube video that has been deleted, made private, or blocked in your region used to end in a generic "service unavailable, please try again" — advice that could never work. Scholarly now tells you the video is no longer available and suggests a different link, and the assistant keeps the conversation going instead of stopping on the error.

Read-aloud narrations stop showing up where they cannot be used

A narration created by Text-to-Speech is saved to your library as an audio file, but it was still offered as a pickable source in the Add content, Flashcards, Quiz, Podcast, Video lecture, Research and document create flows, and in Chat. Choosing one could only ever fail — and in Chat and Podcasts the audio was read as text, so you could get a confident answer built from garbled data. Narrations are now hidden from those pickers, and if one is still attached from before, Scholarly says it cannot be read and suggests attaching the source document instead. Recordings and other audio you upload are unaffected.

Two different narrations are counted as two

Narrating the same document twice with a different voice, speed, page range or title was treated as a repeat of the first request, so the second run was not counted and refunding one could return the other's credits. Each genuinely different narration is now counted on its own, while retrying the same one still counts once.

Repeating a creation in a later week uses that week's allowance

Retrying an older essay or narration weeks after you first made it could settle against the allowance from the week it started — which had already reset — so the work was not counted, and in some cases it went through even when you had already used the week's creations. Repeat creations now draw on the current week's allowance.

Upgrade prompts name the limit you actually hit

Asking for a premium video quality used to open the "Free AI creations used" wall even if you had not spent a creation, and going over a plan's PDF page limit showed an upload or model message instead. Both now open the right screen. The Laureate card in Billing settings also shows your local price rather than always quoting $99.

Fixes across practice, scheduling and downloads

Going back a question during practice no longer clears the answer on screen when the previous question is no longer in your set. Scheduling a task no longer lets you confirm a time that has already passed while the picker sat open, and a scheduled Study Pack now tells you when one of its files could not be queued. Downloading an image from the AI Playground works reliably in Safari and Firefox. The Frontier models help panel is back in the chat model picker, and two Help Center links — Laureate and flagship credits — open the article instead of a Not Found page.

Creations are not cut short or left hanging

A slides, PDF or other document creation that was still running could be marked failed and refunded by our stale-work cleanup, which also stopped the run mid-way. Cancelling an infographic or mind map at the moment it finished or failed could override that result and leave the AI credit unreturned. Downloading a file through our file proxy could hang instead of reporting that the remote server was unreachable. Text-to-Speech no longer fails outright when a language name is not recognised, and the Flashcards file picker no longer offers spreadsheet files it would then reject.

August 23rd, 2026

Scheduled tasks

Schedule any one-time AI creation for a specific day and time instead of starting it immediately. Scheduled tasks from creation windows or Chat stay together on Home, and tasks created inside a project also appear in that project's Tasks view. See exactly when each task will begin or choose Run now to start early.

Images are now first-class files

Upload JPG, PNG, GIF, WebP, BMP, TIFF, HEIC, HEIF, and AVIF images anywhere you add sources — including Home, Chat, folders, projects, and creation tools. They behave like your other files: open them in the file viewer, rename, move, download, archive, chat with them, or use them for Flashcards, Practice Quizzes, Podcasts, and Video Lectures. Images placed inside a page still remain editable image components, so uploading a file and embedding an image no longer compete with each other.

Create options are simpler

Video lectures no longer offer Kids or 480p — resolution is a 720p / 1080p choice, and Dark Mode, Look, and background music sit under More options. Standard lectures always include the companion deck. Podcasts drop Quick Summary. Expert styles are gone from smaller tools such as lesson plans, cheat sheets, PDFs, files, essays, timelines, worksheets, infographics, and mind maps. Infographic and mind map Freestyle is gone too — pick a named look instead. Story Books keep every art style and expert style.

Long podcasts, recordings and videos stream reliably

Playing a long podcast, recording or video no longer fails when the player has to fall back to our streaming route. Files over about 32 MB — which is most full-length podcasts — used to stop with an error even though the file itself was perfectly fine. They now stream in parts, so playback and seeking work the whole way through.

Honest wording when audio or video will not load

When a player still cannot load a file, it no longer suggests your audio or video may need to be uploaded or created again. The message now says what is actually happening — a temporary problem delivering the file — and points you at trying again or refreshing, instead of regenerating an artifact that is fine.

Signed-in visits go straight to Home

Opening scholarly.so while you are signed in now takes you directly to Home. The public landing page no longer disappears while the browser waits to work out where to send you.

Async creations keep their real names

Deep Research started from chat, and other background creations, now keep the title you were given in project lists and completion emails. Finished research no longer shows up as Untitled beside a correctly named research page, and the ready email names the report instead of a generic Research label.

August 22nd, 2026

The Library and Projects load instantly when you come back

Moving between Home, the Library and Projects no longer rebuilds the page you are returning to — each one keeps what it already had on screen. The Library is the clearest win: your filters, your search and the rows you had already scrolled through are all still there, instead of the page starting over from the first screen. Reload the page whenever you want to pull in changes made elsewhere.

A cleaner, quieter interface

We've refreshed the interface so the important thing on a screen is the thing that stands out. Buttons, inputs, and panels now sit on subtle background steps instead of boxes and outlines, colour is reserved for actions and alerts that genuinely need it, and every plan limit — weekly creations, uploads, chat — now looks and reads the same wherever you meet it. Sharing has been rebuilt around a single clear link, and the share dialog no longer shifts as it loads.

A clearer picture when you reach your weekly creations

Reaching your weekly AI creation limit on Premium now shows a notice written for your plan instead of the Free-plan upgrade wall. It names the limit you actually hit, says plainly when your creations come back, and leads with what Laureate adds — 80 AI creations a week, 8× the Premium allowance, plus 1 GB uploads. Credit packs stay available beside it as a one-off option.

See what an upgrade really costs today

The Laureate card now shows the prorated amount you would actually pay today rather than the full monthly price. Stripe credits the time you have already paid for on Premium, so the charge is usually well below $99, and the card spells out both the amount due today and the monthly price after that.

Credit packs compare themselves to a plan

If you have bought credit packs before, the packs window now shows what you have spent this month and what each creation is costing you, next to what the same creations would cost on a plan. No more working the arithmetic out yourself.

AI creations preserve exact source details

Chat, Slides, and Video Lectures now keep signs, percentages, multilingual text, and identifiers exactly as they appear in your source, even when similar values sit beside each other. Exam answer keys also accept answers that match the source's wording and strict numeric boundaries, and medium Flashcard decks stay proportional to shorter sources without awkward duplicated operators.

Slides use the whole canvas

Generated Slides now plan a visual story before drawing, vary their layouts across the deck, and treat excessive empty space as an unfinished slide. Tables render as real horizontal tables with readable headers and columns instead of narrow stacks, and long tables split cleanly across slides.

Finished creations stay ready while Home catches up

Completed Slides and other generated documents remain available from their finished task while they are added to Home, instead of briefly disappearing. Fresh Podcast and Slides pages also load consistently, and completed quiz results use the timeless heading “Quiz results” rather than calling every result today's quiz.

Text-to-Speech: listen to any document as one MP3

A new Text-to-Speech tool reads a document aloud in full and saves it as a single MP3 in your library. Pick it from More tools on Home, or from the creation actions on any file, page, or PDF. Choose from over 25 voices and a narration speed between 0.75× and 1.5×, and Scholarly quotes the exact cost — 1 AI credit per 10,000 words, up to 30,000 words per narration — before you start. It runs in the background and opens the finished audio when it is ready, and formatting characters are stripped so the voice reads prose rather than markup.

Free podcasts and video lectures start on the first try

Choosing the standard 2-minute length on the Free plan no longer blocks the creation. Picking the length we already show you is not an upgrade prompt — only asking for a longer episode or lecture is.

Upgrade prompts open the right plan screen

When a creation needs a paid plan, the upgrade screen now opens with the matching feature highlighted, instead of dead-ending on a “please try again” message or showing a usage-limit notice for an allowance you never spent.

Long prompts from the Home box are handled cleanly

The prompt box on Home now keeps the same 5,000-character limit as the create panel it opens, so a longer prompt no longer fails the whole creation with a technical validation message.

First project setup now asks what you want, then unlocks it

Some new accounts now pick the AI agents they want — video lectures, podcasts, flashcards, study guides, slides, mind maps, worksheets, and chat — right after naming a project. The file you add stays on your device until you subscribe; nothing is uploaded or created on a free plan, and Subscribe later is gone, so the first creation starts after checkout.

August 21st, 2026

Chat keeps working after you leave

You can close the tab or move to another page while Chat is answering. The response keeps running in the background, and reopening the conversation reconnects to the same answer without starting it over. Stop still ends the active response.

See which model answered each chat

Recent chats and Chat results in quick search now show the AI model used in that conversation, with its provider icon. If you switch models or choose a different retry, the label follows the latest active answer.

AI models now use one simple credit balance

Frontier Boosts have been replaced by model-based AI creation costs. Standard models use 1 credit, while Frontier models GPT 5.6 Sol and Claude Opus 5 use 3. Every paid plan can choose the full creation-model catalog; Sol and Opus are no longer offered in unlimited Chat.

One reusable profile for every AI creation

Customization Profiles replace separate Saved Instructions and Custom Designs. A profile combines reusable instructions, a preferred AI model, and visual references such as logos, brand guides, or templates, then applies to any creation while one-off instructions and format-specific themes stay available. Choose a profile from the new button at the top of every Customize step. Existing saved instructions and designs are kept and moved into Personal profiles automatically. Team admins can publish and edit shared Team profiles from the new Profiles tab on the team page, and each Project can choose a default profile for consistent chats and creations.

Choose between Personal and Business plans

Plan options now open with a Personal and a Business tab, so you can price a plan for yourself or per seat for your team without leaving the window. Being in a team no longer locks you out of a personal plan, and you no longer need a team to see Business pricing — pick a plan there and you'll be asked to name your team next. Yearly and Monthly have moved inside each plan card, so the price you are choosing sits next to the plan it applies to, and Laureate no longer shows a billing choice it never had. Team members who cannot change the team plan can see Business pricing and are pointed to a personal upgrade instead of a dead end.

Team setup now shows what you're buying

Setting up a team used to offer two one-line plan summaries. It is now a full-screen, three-step flow — name the team, choose a plan, choose seats — and the plan step lists everything each seat gets, the same way personal plans are shown. Seat pricing, the yearly saving, and the running total are all visible before checkout.

The pricing page now matches the in-app plan picker

/pricing uses the same plan cards as the upgrade window, so the plans look and read the same wherever you see them. The Teams tab is now called Business, Yearly and Monthly have moved inside each plan card, and the term you pick there is the one carried into checkout — previously the pricing page could only start a yearly Premium checkout. Business now shows Premium for Teams and Laureate for Teams side by side; schools and organization-wide rollouts are covered by those same plans, so the separate educators box has been removed.

Choosing a plan no longer restarts onboarding

Picking a team plan could drop you back onto the last slide of new-account onboarding, even if you had finished onboarding long ago. Onboarding now runs once and only once; choosing a plan takes you to team setup instead.

More file types in your first project

Some new accounts using the guided first-project setup can now add the same local files as Add Content: documents, spreadsheets, text files, images, audio, and video. The next step only offers creations that can use those sources, so an upload is not silently ignored; saved first-project drafts also keep images, videos, and recordings.

Flashcards tell you when a file was left out

A file Scholarly can't read as text or an image is now named as it's skipped, instead of quietly disappearing from the deck — this most often hit files dragged in without a file type, such as a PDF or a file with no extension. The sources that did work keep the order you picked them in, and when the skipped file was your only source, the message names the file and says what to add instead.

August 20th, 2026

A guided first project for new accounts

Some new accounts now start by naming a project, saying what the material is for, adding a file, URL, or pasted text, and choosing what Scholarly should create. The recommendations match the goal you pick, whether that's a certification, work material, research, teaching, or coursework, and study guides, practice sets, slides, flashcards, videos, podcasts, and mind maps are all available. A new setup step tunes that creation before it starts — style, length, deck size, resolution, and AI model — and files that are too large or over your upload allowance are now named on the spot with the upgrade that lifts the limit. Free projects build one creation at a time; paid plans pick several at once and unlock the longer, higher-quality settings.

Team checkout no longer stalls on a server error

Starting a team or workspace checkout could fail with a server error that then repeated on every retry, because a background database step could get stuck on the machine handling your request. That step no longer runs during checkout, so the page opens Stripe as it should.

Lower, simpler Teams pricing

Premium for Teams is now $35 per seat each month or $336 per seat each year, and Laureate for Teams is $110 per seat each month or $1,056 per seat each year. Annual billing is 20% less than paying monthly for twelve months.

Saved web pages keep their study material

Pasting or uploading a saved web page could be rejected as “not enough study material” even when the page held a full set of notes: pages that build themselves with scripts keep their content out of the saved markup, so only the buttons and menu labels were read. Scholarly now reads the material those pages carry, so your notes come through and the cards are built from them. When a saved page really does hold nothing but the page shell — because its content is fetched fresh every time it opens — you are told so straight away, with what to add instead, rather than after a creation has already been spent.

Team upgrades now stay with the team

In a Team workspace, upgrade buttons now say Upgrade Team and open per-seat Team pricing instead of an individual checkout. Owners choose Premium or Laureate, then set the number of seats for the whole team; members are directed to the person who manages billing. Skipping the first plan choice now opens Home with the Team welcome, canceling checkout returns Home without the personal checkout offer, and the duplicate Choose plan button has been removed from the Team page.

Companion slide decks stop restarting finished videos

When you asked for a video with a companion slide deck, the deck could fail to build even though the video itself was finished, throwing away the whole generation and starting it over. The deck now reads the same lecture timeline the video was rendered from, so it exports on the first pass.

Long research turns in Chat answer before they run out

A Chat turn that spent a long time building files, running commands, and checking images could use up its whole step budget and end with nothing written. Scholarly now reminds the model of the steps it has left as it approaches the limit, so it writes up what it found instead of finishing empty-handed.

Chat already knows the source you're on

On videos, PDFs, flashcards, podcasts, recordings, research, folders, files, notes, projects, and the image playground, an empty chat now says it already has the source in front of it, so you can ask straight away instead of describing what you are looking at. New accounts start with the chat rail open; if you have shown or hidden it before, Scholarly keeps your choice. The main Chat page is unchanged.

Video lectures keep completed narration

Two-minute video lectures no longer fail when a generated narration scene runs a few seconds longer than its estimate. Scholarly keeps the completed audio, finishes the video, and applies the length limit before starting any additional narration.

Plan options now show podcast and video length

Free, Premium, and Laureate now list how long podcasts and video lectures can be. Free stays at 2 minutes; paid plans go up to 60-minute podcasts and 45-minute video lectures.

August 19th, 2026

A clearer upgrade path in the model picker

Models that need a paid plan now carry an Upgrade badge in Chat and in every creation tool, and choosing one opens your plan options instead of failing when you send. Previously a recommended model could look available and then be rejected.

One email when a creation is ready

Settings → Notifications now has a single “When a creation is ready” toggle. Scholarly emails you when any long-running creation finishes — podcasts, video lectures, study guides, PDFs, slides, research, and the rest — not only podcasts, videos, and flashcards. Uploaded PDF processing and meeting-notes transcription still do not send an email.

August 18th, 2026

Recommended models stay on the first screen

The model picker in Chat, Research, and every creation tool now lists Recommended Models on the main menu, right under Auto. Auto rows no longer show the current underlying model as a subtitle.

Retrying an older video lecture just works

Retrying a video lecture built with a model we have since replaced now re-runs it on your plan's current model, instead of asking you to start over with a new request.

Video narration survives a provider outage

If the speech service has a brief outage, video lecture narration now waits and retries instead of failing the whole lecture. If it still cannot finish, the error explains what went wrong instead of a generic failure message.

One input that runs every tool

Home's input now carries the whole toolbox along its top. Pick Chat, Image, Document, Deep Research or Essay and describe what you want; pick Study Guide, Slides, Mind Map or Worksheet and drop a PDF, doc or deck straight onto it. What you type or drop is carried into that tool's setup instead of being asked for twice, and everything else sits under More tools. Chat is the real chat input, so linking sources, pasting, attachments, the model picker and voice all work before you leave Home.

Linked sources appear as soon as you send

Attaching a page, folder, recording or file to a chat message left an empty grey bubble above your message until you reloaded the conversation. The attachment now shows up as a labelled chip the moment you send it.

Flashcards tell you what they skipped

When a source can't be used yet — a PDF still processing, a video still transcribing — flashcards build the deck from everything else and now tell you exactly what was left out, instead of quietly making a smaller deck.

Generations recover instead of vanishing

Study guides, slides, worksheets, reports and other documents now keep generating even if you leave the page. A generation that used to stop mid-run now finishes, or fails with a real reason and your credit back.

An interrupted generation no longer starts over

If a generation is interrupted part-way through, Scholarly now picks it back up with your sources still in place — instead of throwing the whole run away and starting over.

Rename a project or meeting notes from its title

The big title at the top of a project workspace and of AI Meeting Notes is now editable. Click it, or the pencil beside it, and type — the same rename that used to be possible only in the small breadcrumb at the very top of the window. Both places stay in sync and save as soon as you press Enter or click away.

Rename a folder from All Content

The folder right-click menu in All Content offers “Update Name” — it now opens a rename box instead of just opening the folder. The name is pre-filled, Enter or Save applies it, and you stay on the page.

Long recordings keep their whole live transcript

The live transcript of a very long recording no longer drops its earliest lines. Lines now break at natural pauses, so a multi-hour session keeps the full transcript.

Sharper generated artifacts across the board

A sweep of the AI generators fixed defects found by auditing real generated work: true/false exam items no longer mark a correct restatement false, mind maps render every label at a readable size instead of shrinking to fit, slide decks stop leaving the bottom quarter of the page empty, and video lectures now respect the length you picked instead of overshooting it.

Recordings keep their own language

A lecture recorded in Spanish, French, or German now gets its summary, topics, and title in that same language instead of English. Long recordings are also no longer mistaken for empty ones, and stretches where nothing was captured are marked rather than quietly filled in.

Abandoned recordings stop blocking new ones

A capture interrupted by a closed tab or a sleeping device no longer leaves your account stuck behind a recording that never finishes. It now expires on its own, and any audio already saved stays available to process.

Quoted text in other scripts survives

Documents that quote a title in Hindi, Arabic, Russian, or Chinese now render that text properly instead of dropping or translating it to get the file to build.

Checkpoints and chapters span the whole video

On long videos, learning checkpoints and chapters previously clustered in the opening minutes. They now spread across the entire runtime, and checkpoints that used to be silently discarded are kept.

Watch your recording transcribe itself, live

AI Meeting Notes now stream the transcript as you speak. Lines are cut at natural pauses rather than on a fixed timer, so each phrase appears within seconds of you saying it, and a live status under the transcript tells you whether we are listening, transcribing, or hearing nothing at all. The moment you finish, the transcript is already there while the summary and action items are written.

Record anywhere in Scholarly

Capture lives in one small floating bar at the bottom of the screen. It follows you across the whole app with the elapsed time, a live level meter, and pause and finish always one click away, so you can take notes, open a source, or start a chat without ending the recording. Leaving the recording page no longer stops capture.

A calmer recording page

The recording page now leads with its title, status, and date, then a single card holding Transcript, Summary, Action items, and AI Creations. It fills the screen properly at any window size, and every empty tab says what will fill it instead of sitting blank.

Clearer recording warnings and errors

Every recording warning and failure — a blocked or silent microphone, an interrupted capture, an unsupported browser, a failed processing run — now appears as one consistent, persistent notice with the fix or retry attached, instead of assorted inline boxes and toasts that disappeared before you could read them.

Japan-specific exam pages

Japanese visitors now get dedicated exam pages for 宅建, 日商簿記, ITパスポート / 基本情報, 医師国家試験, TOEIC, and 社労士 — written for those exams, not translated from US tests. The Japanese homepage and exam-prep pages link to them.

AI Document is the one file creator

Reports, timelines, SOPs, spreadsheets, mind maps, and the rest now start from one AI Document page. Older tool pages still work and send you there, and there are new pages for reports, case studies, and rubrics.

August 17th, 2026

Buy AI creation credits

Paid plans can now buy one-time AI creation credit packs — 5 for $15, 15 for $30, or 40 for $60. Credits never expire and are used automatically once your weekly allowance runs out. Find them in Billing settings or right where you hit the limit.

Free AI Chat allowance

Free AI Chat now includes 3 messages total. The allowance remains account-wide and does not reset; Premium includes unlimited AI Chat.

A simpler Home

Removed the Up next card from the top of Home. Weekly Brief still appears when available; otherwise, your projects and content follow the creation tools without another recommendation panel.

Retrying a video lecture recovers properly

Retrying a failed video lecture now restores its full automatic recovery, so a run that previously gave up immediately gets a real second attempt.

Laureate pricing in your currency

The plan modal and pricing pages now show Scholarly Laureate in your local currency — the same $99/month converted at current exchange rates, matching exactly what checkout charges.

AI Meeting Notes survive sleep and mic dropouts

Live capture now detects when your computer goes to sleep, the tab is suspended, or the microphone dies mid-recording. It automatically restarts the mic where possible, warns you on the spot, and clearly discloses on the finished notes how much time went uncaptured instead of quietly delivering a partial recording.

Clearer free chat limit handling

Hitting the free AI Chat allowance mid-send now shows the proper upgrade path instead of a generic error with a Retry button that could only fail again.

August 16th, 2026

Laureate upgrades in every billing currency

Premium members billed in a local currency (like EUR, TRY, or INR) can now upgrade to Scholarly Laureate in-app — the same $99/month, converted to your subscription's currency at current exchange rates.

More reliable AI generation

Question-bank flashcard decks no longer fail when part of the source — like a video's outro — contains no questions. The deck now completes from the sections that do.
Video Lecture narration now recovers automatically from brief audio-service connection drops instead of failing the whole video.

Clearer creation and navigation states

Chat now correctly explains that AI Meeting Notes use the file-upload allowance rather than an AI creation.
Home no longer offers processing or failed items as ready to open, and flipping through Slides quickly no longer blanks a page that is still loading.
Mobile timestamps are easier to read in light mode, and the yearly billing badge stays inside its option card on the exit offer.

A Weekly Brief that belongs on Home

Weekly Brief now uses the same calm, neutral design as the rest of Home, with a clearer reading hierarchy, a focused Ask AI prompt, a cleaner self-check, and a simpler way to add material for next week.
Your first Weekly Brief can now be created after one full day as a subscriber instead of waiting five days, as long as you have recent material to use.

Start at 2 minutes, then make it longer

Free podcasts and video lectures now use a fixed 2-minute length. A persistent Make Longer banner can upgrade and replace either item in the same spot without using another creation credit; the original stays available until the longer version is ready.

Stop active creations from Chat

Ask Chat to stop an active podcast or AI video lecture. Scholarly now cancels the running work, marks it as cancelled everywhere, and does not leave it running in the background.

Video lectures keep text readable in every language

AI video lectures now include the fonts needed for Thai, Hindi, Arabic, Chinese, Japanese, Korean, and other scripts. Missing characters are repaired automatically instead of showing as empty boxes.

Reliable captions for Short and Kids videos

Short and Kids & Story video lectures could fail to finish when the narration contained certain words. Caption matching now handles every word, so those lectures complete and caption normally.

August 15th, 2026

One AI Document creator

PDFs, reports, timelines, SOPs, spreadsheets, tables, exports, calendars, and more now start from one AI Document tool with a single source picker and document-type chooser.

Create the workspace, then choose seats

Registration again asks whether you're starting personally or with a team. Choose Team to name the workspace, then set the number of seats and choose Premium or Laureate. The same setup is available later.
Not ready to pay? Try the owner workspace with your personal plan. Invitations and join links unlock after checkout, and returning later keeps the same workspace and content.

Clearer limits and smoother account flows

AI Chat now asks before sharing product feedback with the Scholarly team and waits for your explicit approval.
The welcome tour and exam results now describe Free chat, quiz, voice, and exam allowances as lifetime limits that do not reset.
Registration can be submitted with Enter, Settings billing links open the Billing tab, the Home composer is easier to see in light mode, and plan comparisons fit more comfortably on screen.
The post-purchase welcome no longer asks you to change billing periods before returning to your work, and monthly members no longer see a generic yearly-billing popup during ordinary sessions.
When more than one Free allowance is reached, Home now names exactly which allowances were used instead of implying every feature is exhausted.
The Flashcard upload helper now lists PowerPoint alongside the presentation files it already accepts.

Fix flashcards without spending another creation

Repair Card, whole-deck Refine with AI, and card changes requested in deck chat no longer use an AI creation. New flashcard decks and new cards generated from sources still use the normal allowance.
Card repairs and whole-deck refinements now use medium reasoning for more reliable corrections.

Math video animation

The Math video mode now starts with polished, source-grounded animated scenes when one fits. Other math topics still use the existing math-video style, so the lecture finishes either way.

A steadier Home while it loads

Home now waits for your workspace to finish loading before choosing a layout, so new accounts no longer see the wrong screen flash by before the getting-started view appears.

August 14th, 2026

More forgiving flashcard creation

When you upgrade from Add content, Scholarly now restores the files, pasted text, links, Library items, and Google Drive sources you selected before checkout.
A completed flashcard deck with fewer than 15 cards no longer uses an AI creation. Scholarly tells you when the creation was returned and suggests adding more source material.

Stronger Auto flashcards

Premium Auto flashcards now use Gemini 3.7 Flash with medium reasoning, while Laureate uses high reasoning. Free stays on GPT 5.6 Luna.

AI Image Playground is out of beta

The Playground no longer has a separate daily beta cap. Each new image or reference-image edit uses one AI creation per selected model, and failed generations are refunded automatically.
Images created or edited in regular AI Chat do not use AI creations; the normal Chat message allowance still applies.

Video blocks on pages

Dragging a video file onto a page's video block now uploads it. Previously the drop did nothing and you had to click through to the file picker.
Switching between the Upload and YouTube Link tabs no longer clears the link you typed or the file you picked.

More room to try Free, with clearer limits

Free AI Chat now includes 10 messages total instead of 3 per day. The allowance follows your account and does not reset.
Free autocomplete, quiz practice, voice mode, and practice exams are now clear lifetime allowances: 500 words, 5 questions, 15 minutes, and 1 completed exam attempt.
Settings, upgrade screens, pricing, and Help now show lifetime usage consistently. Failed Chat responses return their reserved message, and only completed exam attempts count.

Explore, blog and preview read properly on a phone

The featured lecture on Explore no longer has its title cut off, and the podcast and video charts fit the screen instead of running off the right edge.
Comparison tables in blog posts scroll sideways on a phone instead of silently losing their last columns.
File preview opens edge to edge on a phone, PDFs open fitted to the screen width, and the file name is no longer squeezed out by the toolbar.

Controls you can actually hit on a phone

Dragging the podcast and recording progress bars now scrubs, instead of jumping to a chapter, because the chapter markers no longer sit on top of the whole bar.
Model pickers and other menus opened near the top or bottom of the screen now flip or slide into view instead of opening into an unreachable sliver.
A notification that offers an action, like opening a deck the moment it finishes, now waits for you instead of disappearing after a couple of seconds.

Flows that were stuck on small screens

Focus mode results no longer cut off the score at the top and the buttons at the bottom.
Long exam answer choices are shown in full on a phone instead of being clipped after three lines.
The image playground opens on your images on a phone, with the chat a tap away, instead of the chat covering the whole screen.
The page export dialog stacks its options and preview on a phone and keeps Export within reach.
Plan limits and upgrade prompts stack properly on a phone, and the feature explanations on the pricing table can be tapped open on touch screens.

August 13th, 2026

Laureate upgrades that finish in Scholarly

Premium members can now review the exact prorated amount and confirm a Laureate upgrade directly in Scholarly, without being sent through the billing portal.
If Premium was scheduled to cancel, confirming Laureate now reactivates the subscription as part of the same upgrade instead of asking you to fix billing first.

More reliable source tools

The chat button on PDF, presentation, recording, podcast, video, and other content pages now reliably opens the assistant.
If you press Send after reaching your Chat limit, Scholarly now opens the plan comparison instead of appearing to do nothing.
Chat, Podcasts, and Video Lectures now preserve requested source identifiers character for character, including multilingual text, spaces, and punctuation.

Gemini 3.7 Flash

Gemini 3.7 Flash replaces Gemini 3.6 Flash across Chat, Research, Slides, Video Lectures, and Infographics. It is Google's latest Flash model for chat, research, and visual work. Saved 3.6 Flash picks return to Auto, and you can choose 3.7 Flash from the picker.

Clearer file size limits when you add content

If a file is too large, Add content now names your plan's size limit, the size the next plan unlocks, and what to try instead — split a long PDF, trim a recording, or paste the text you need.
The "Add more files" area also shows the size limit before you pick a file, so you know the cap without hitting it first.

Research files carry across follow-ups

Every new report in a Research session now starts with the files you uploaded and the files earlier reports created. Research Chat can also inspect those saved files directly when you ask about them.

Clearer downloads on Free

On the free plan, Download is now the main button when you save a video or file — it opens upgrade so you can keep a copy on your device. Copying a share link is still free, as the secondary action.

Clearer creation controls

Every AI creator now gives custom instructions the same 5,000-character allowance, and selected presets and designs always show a checkmark.
Chat limits now explain when they reset without interrupting your draft, and podcast and video tabs keep their full labels on smaller screens.
Two-speaker podcast requests now stay limited to the host and guest throughout transcript and audio generation.
The AI Video Lecture creator now opens immediately instead of showing a dark loading pause on its first launch.

A quieter model picker

Chat and AI creation no longer tag every Frontier model with a Frontier badge. Those models still live under Frontier Models, and Laureate still has Frontier Boost.

Study questions on every card

A batch of cards could occasionally come back with practice questions for only one of them, leaving the rest blank in study mode. Those cards are now regenerated automatically.

More reliable source creation

Every creation dialog now checks a pasted website as soon as you add it and shows the same recovery steps. Blank pages, loading screens, sign-in walls, and empty app pages never enter the source list.
Flashcards now retry once on another compatible AI model when a readable page with clear definitions, requirements, regulations, or questions is incorrectly dismissed as blank or front matter.

AI Image Playground

AI Image Playground now appears directly in Home's Create with AI tools, so you can start generating and editing images without opening More first.
A new Playground chat turns natural-language requests into background image jobs. Model, aspect ratio, and quality controls provide defaults, while follow-up instructions can override them without touching a dropdown.
Home tool labels no longer get their letters cut off at larger browser zoom or display scaling.

Chat file preview

PDFs created in chat open in the side preview again, instead of saying the file type is unknown. Images and other chat files saved without a file extension preview the same way.
Chat can now preview notes and files that were saved without a full file type, downloaded PDFs keep a .pdf suffix even when the title has no extension, and duplicated videos and flashcard images still play.
Spreadsheets and files created in chat now open in the side preview instead of leaving the conversation, and downloads from the file page keep the right extension.

August 12th, 2026

Feature and use-case pages

Every feature, use-case and landing page now opens with a real product screenshot beside the headline instead of a wall of text, so you can see what Scholarly does before you scroll.
Added product previews to pages that previously had no imagery at all.
Feature and use-case pages now share the same headings, cards, and spacing, so they look consistent from page to page.

More AI models for Premium

Grok 4.6 from xAI replaces Grok 4.5 across chat and create tools. It stays a recommended Frontier model, thinking is always on, and previous Grok 4.5 and Grok 4.3 selections continue automatically.
Premium now includes recommended access to Grok 4.6, Claude Sonnet 5, Gemini 3.1 Pro Preview, and GPT 5.6 Terra. The full supported catalog is also back under More Models, while flashcards keep GPT 5.6 Luna as their focused recommendation.
Scholarly now remembers the model you choose for each AI creation tool, including Podcasts, Video Lectures, Research, and Slides. Auto stays on Auto and continues using the current recommended model.

Grok Imagine 2.0

Grok Imagine in the AI Image Playground and Scholarly's shared xAI image tools has been upgraded to Grok Imagine Image 2.0 for image generation and reference-image edits.

A clearer pricing page

Rebuilt the pricing page from scratch. Plans and prices now sit at the top of the page instead of below the fold, each plan says who it is for in one line, and the plan comparison table fits on screen instead of scrolling sideways and cutting off the Laureate column.
Teams is two seat plans on the pricing page: Premium for Teams ($45/$324) and Laureate for Teams ($135/$972), under a Personal / Teams switch.
The pricing page no longer has a monthly/yearly toggle. Premium is yearly-only and shows the monthly price instead of the yearly total.
Laureate now leads with what it actually unlocks: the full Frontier model catalogue — Claude Opus 5, Gemini 3.1 Pro and Grok 4.6 — which no other individual plan includes, on 20 creations and 20 chats each week.
Laureate creation Frontier Boosts doubled from 10 to 20 each week. Its 75 total weekly AI creations and 20 Chat Frontier Boosts are unchanged.
Standard video lectures now let you pick a color look — or apply a saved custom design — without leaving Standard. Companion slide decks are included automatically.
Auto (Laureate) now uses Claude Opus 5 at low reasoning for Frontier work. After weekly Frontier uses are gone, Auto continues on GPT 5.6 Luna.

More reliable YouTube transcripts

A YouTube video that needs transcribing is now processed once and reused wherever you request it, instead of occasionally failing or being transcribed again when several requests arrive together.

Longer free podcasts

Free podcasts now run up to about 15 minutes — a commute-length listen. Upgrade still unlocks a longer target length.
Podcast now sits with Flashcards and Video Lecture on Home, after you upload, in the New menu, on source AI actions, and as a first-run welcome choice.

Longer free video lectures

Free AI Video Lectures now use Auto length — sized to your sources, typically a few minutes — instead of a fixed 2-minute length. Paid plans can pick a specific length up to 45 minutes.

A quieter Home

Folders on Home now appear above Content, keeping organized work visible before the unfiled content list.
Home no longer shows the Discord community banner or the Teams work contact card. You can still join Discord from Help, Settings, and the profile menu, and contact us about Teams from pricing and billing.

Quality and consistency fixes

Word and PDF page controls now move immediately and reliably, including when you reach the last page of a short document.
A video lecture's companion deck download now names the slide deck, rather than incorrectly calling it a video.
AI Slides now reuse the same rendering for a formula that appears more than once, so signs, decimals, superscripts, and subscripts stay identical across the deck.
The homepage feature tour no longer repeats Flashcards, and audience proof across the homepage, upgrade screens, onboarding, and community prompts now consistently says 170,000+ users.
Billing now shows Laureate directly alongside Premium and opens its $99/month checkout path. Plan details clearly separate unlimited standard-model Chat from 20 weekly Frontier Chat boosts, and Stripe checkout summaries now list concrete Premium and Laureate allowances.
Chat now preserves source numbers character for character when exact formatting is requested, including leading plus signs, trailing zeros, precision, units, and inequality symbols.

August 11th, 2026

Chat with your Research

Research is now a focused workspace with Report, Sources, and Create tabs, plus a dedicated chat. Ask for a grounded summary, compare findings, challenge a conclusion, or inspect the evidence without leaving the report.
The chat is now the single place to request follow-up research. It can start another background report inside the same Research session, where report history sits beside the chat and progress updates automatically.

Deep Research: from sources to a finished result

Starting Deep Research from Home or an old Research link now opens the same guided source-to-result workspace. Add files, folders, saved Scholarly content, Google Drive files, URLs, or a prompt; then set the research objective, depth, evidence priorities, and model, and choose at least one additional deliverable such as a study guide, comparison table, CSV, timeline, or one-page brief.
Research now keeps Report, Sources, Files, and AI Creations in separate tabs above the workspace, gives an active research plan clearer visual separation while it runs, and starts new setup forms at Medium depth.

Simpler AI model controls

Chat, Research, and AI creation now share one consistent model selector with Auto, Auto (Premium), and Auto (Laureate) visible on every plan. The bottom Frontier Boost toggle switches Auto (Laureate) between Claude Sonnet 5 and GPT 5.6 Luna.
Laureate's 75 AI creations, 10 creation Frontier Boosts, and 20 Chat Frontier Boosts now reset every week instead of every month.
Creation setup panels now use consistent, larger section titles and descriptions across designs, expert styles, settings, custom instructions, and Study Packs.

Clearer Premium plan details

The upgrade screen now lists Export & download and Priority support alongside the existing Premium benefits.

Premium and Laureate for Teams

Teams is now two seat plans: Premium for Teams and Laureate for Teams. Every seat inherits that plan's models, features, and limits, plus a shared library, roles, and one bill. A stronger personal plan still wins. There is no team credit wallet.
Start with 1 to 29 seats, monthly or yearly. Admins get a cleaner Team page with Overview, People, Library, and Plan, plus a 7-day activity view.

Flashcards: new AI & Sources tab

The Sources tab on every flashcard deck is now AI & Sources. Create a podcast, video lecture, study guide, and more straight from the deck's original source material, and see everything else already created from it — all without leaving your deck.
"Created from this" lists across the app now update the moment a generation finishes — no page reload needed.

Regional Pricing

Premium is now ₹1,299 per month or ₹6,199 per year in India. The yearly option keeps the same Premium access while saving about 60% compared with paying month to month.

Bug Fixes

YouTube videos with captions are no longer rejected as "no captions available" when the transcript service is briefly busy. Uploads now retry automatically, and if it's still busy you'll see an honest "try again shortly" message instead.
Anki flashcard import now supports decks exported by Anki 2.1.50 and newer. Corrupt deck files also get a clear explanation instead of a technical error.
Uploading a video that has no audio track no longer fails with a technical error — the video now imports normally, with transcript-based features simply unavailable.
When a chat reply reaches the four-image generation cap, the assistant now finishes its answer with the images it already created instead of the whole reply failing.
Cmd+K and Ctrl+K now open workspace search immediately with the search field ready for typing.
Workspace search now shows content and chats together without extra filters, and the window stays the same height while you type so results no longer shift the layout.
Flashcard decks now show how many Questions are ready directly in the tab, without waiting for you to open Questions first.
Long YouTube videos without captions now finish transcript processing reliably instead of sometimes appearing to have no transcript while processing.
Signing out or switching accounts in the same tab now clears the previous account's library completely. Files from the earlier session no longer appear on Home, in the sidebar, or under All content, and the new account's own content loads right away instead of leaving the workspace empty.
Help chat history, active study sessions, questions marked as hard, and podcast progress checks now reset on sign-out too, so nothing from the previous session carries into the next account.
After sign-up, the onboarding handoff now keeps a clear loading indicator on screen and warms the next workspace view, instead of flashing a blank page before the welcome flow appears.

August 10th, 2026

Explore: dedicated podcast, video, and flashcard pages

Explore now has purpose-built public pages for podcasts, videos, and flashcards. Podcasts get a featured player and a ranked episode chart, videos a cinematic billboard and thumbnail wall, and flashcards an interactive sample card you can flip — every item is real community content, in English and Japanese.
Podcast and video items across Explore now include episode duration and chapter counts.

Bug Fixes

Chats can now reference earlier chats. Type @ to find a previous conversation and bring its user and assistant messages into the current discussion.
Typing @ in Chat now searches your complete library, so older pages, files, recordings, podcasts, Research sessions, and folders remain easy to find even when they have not been loaded yet.
Upgrade and download dialogs now close cleanly when you sign out or switch accounts, so the next account never inherits the previous session's content or action.
AI Meeting Notes mentions in Chat now use their red recording accent instead of appearing as a generic grey upload.
AI Video Lectures now keep signed values from their sources, leave behind-the-scenes production notes out of the narration, and reliably include a requested companion slide deck.
Returning to a Chat now restores a completed answer, document paging reaches the final page and has accessible controls, and AI creator instruction counters and upload limits explain exactly what is blocking the next step.
Free Exam screens now explain the one-attempt daily allowance and when it resets.
PDFs chosen from a folder's Import screen now continue through the normal uploader and save back into that folder, and uploaded images remain visible there too. File pickers also match the formats the uploader supports, and cloud-synced files show a clear retry message if access is lost.

August 9th, 2026

Bug Fixes

Fixed Illustrated and Short video lectures failing with "Failed to render the video" or drifting out of sync with their narration — the finishing step now preserves the silent beats between scenes instead of collapsing them.
Large Word and PowerPoint documents now convert reliably for reading in chat and Google Drive imports, up to your plan's file-size limit — previously anything over 32MB failed with a raw server error.
Opening Home directly now loads recent chats and existing workspace state correctly, instead of sometimes showing the new-user empty screen until you visited Chat.
Video lecture pages are cleaner: companion decks now open in a Slides tab, and the redundant AI Generated badge is gone.
Companion slide decks are now included for Free members too and are enabled by default for every Standard AI Video Lecture. Everyone can review and present the deck in the Slides tab; downloads remain a Premium feature.

August 8th, 2026

Video Lectures: color variety and Dark Mode

Standard video lectures now draw from a pool of hand-tuned color palettes — soft pastels, brights, and editorial wildcards alongside the classic cream-and-blue — so each new lecture gets its own look while keeping the same clean design. Charts, cards, and embedded diagrams all follow the drawn palette.
A new Dark Mode toggle in the video creation panel renders every slide on a clean dark theme, drawn from five dark palettes with matched accents and chart colors.

Stronger reasoning in paid Auto

Paid Auto now uses high reasoning effort in Chat and agent-powered AI creators, including Research, slides, documents, video lectures, infographics, and podcasts. Flashcards keep their balanced medium setting, and Free Auto remains unchanged.

Video lectures can include a slide deck

Every Standard AI Video Lecture can include a companion PDF deck, with the option enabled by default on every plan. Each page captures the completed teaching scene, and the finished deck opens in its own Slides tab without using another AI creation; Premium members can also download it beside the MP4.

Bug Fixes

Fixed chat turns that could spend the entire turn running web searches and end with a “used all of its research steps” error — the assistant now wraps up and answers from the results it already gathered.
Stopping a new Chat answer now works reliably even when the stream is still starting, instead of sometimes leaving the answer running.
Switching away from the Library tab in an AI creator now preserves the folder and loaded page you were browsing. AVIF images imported from a URL are also recognized correctly.
The docked podcast player keeps its chapter label aligned after a chapter seek, and study progress is cleared and isolated when accounts change.
Older study-guide paragraphs render again instead of disappearing, and pill-style selectors now keep their intended fully rounded shape at every size.
Shared flashcard study guides now verify that the deck belongs to the page being viewed, keeping another deck's highlights private.
Settings, sharing, and other dialogs now open above the entire page, including an expanded podcast chat, so every control remains visible and usable.
Downloads now consistently require Premium across Chat podcasts, file and Office preview fallbacks, and AI Playground images. Free members see the share-or-upgrade choice instead of downloading directly.

Clearer content tabs

AI Creations and source lineage now share one AI & Sources tab across podcasts, video lectures, PDFs, files, and Research, keeping the same create, related-output, and source details together.
Podcast Producer Notes and Related Resources are gathered into one Deep dive tab, and the bottom player stays pinned while signed-out listeners browse a shared episode.
Podcasts with chapter slides now gain a synchronized Video mode and a share-ready MP4. Video rendering happens separately so the finished audio stays available; MP4 downloads are included on paid plans.

Calmer podcast and video pages

The episode header no longer repeats the cover art, title, and duration the player already shows. It is one details line with the summary folded to two lines, so the slide, the tabs, and your chapters all fit on screen without scrolling.
Chapters are now a numbered list you can scan and jump from, on both podcasts and video lectures. The sideways-scrolling cards are gone, along with the shrunken copy of the slide that was already playing above them.
Fewer, clearer tabs. Producer Notes and Related Resources become Deep dive on podcasts, and video Questions moves into the tab row instead of sitting permanently open between the player and everything else.

August 7th, 2026

Premium plan updates

Premium includes 10 AI creations each week, shared across flashcards, podcasts, video lectures, slides, documents, Deep Research, and the other AI creators. The allowance resets every Monday.
Settings → Billing now shows your live weekly usage. A failed creation returns its slot automatically, and reaching the limit leaves all existing work available while showing the next reset clearly.

Expert styles in every AI creator

Every AI creation panel now offers format-specific expert styles beside the other creative choices — including quizzes, essays, reports, case studies, rubrics, cheat sheets, and general documents. Quiz styles and custom instructions now also steer the generated questions.

The podcast player now docks at the bottom

The episode player sits in a bar pinned to the bottom of the page — play, skip, speed, and your position in the episode stay in reach while you browse chapters, the transcript, and questions.

Podcasts now come with a research layer

New podcasts include timestamped Producer Notes that add researched context at the moments where it matters. Jump back to the exact point, follow the cited links, or send a note straight into the podcast chat to explore it further.
A Related Resources section curates trustworthy websites, papers, archives, courses, and exhibits for continuing beyond the episode. The same enrichment pass also creates the listening check-in questions, so every extra is planned together while the audio records.

Home opens with your next session

Home now leads with a continue card that names your single next step — cards due for review with a time estimate, the deck you were mid-way through, or your latest material — so returning never starts from a blank page.
The welcome-back popup is retired. After a few days away, Home itself greets you with what's waiting instead of interrupting with a modal.

A calmer Home

Create with AI now leads with the tools people actually reach for, and moves the rest one click away under More — so the row is scannable instead of a wall of chips.
"Jump back in" is gone: it repeated the same items already listed under Content, and the continue card at the top of Home now covers picking up where you left off. Folders move below your work and appear once you have one.
Creation tiles and chips across Home and the upload flow share one flat, consistent button style in both light and dark mode.

Folders are just your folder now

A folder page is now its name, a search box, New, and your content — the wall of creation tiles is gone. Everything you could make from a folder is still one click away under New, and new content still saves into the folder you're in.
Search filters the current folder as you type, across both its items and its subfolders.

Consistent sections on content pages

Chapters, Summary, Transcript, Tasks, AI Creations, and Sources now share one clear card layout — a titled card with its own icon and actions — across video lectures, podcasts, AI Meeting Notes, PDFs, files, pages, and flashcard decks.

Uploads

AVIF images can now be uploaded anywhere images are accepted — they're converted automatically, so flashcards, chat, and page uploads all work with them.

Study, pages, and library polish

Free Study consistently stops after five questions, including when Next is pressed quickly, and its Questions count now shows the real daily allowance. Flashcard controls also stay single and readable before and after a card is flipped.
Pages now open directly as one editor without an extra AI Creations tab. Pasting from Google Docs, Word, and other rich editors preserves headings, bold, italics, underline, links, lists, quotes, and tables while still recognizing Markdown-style headings and quotes.
Two-host podcast requests now stay at exactly two voices, delivery directions no longer leak into transcripts or speech, and finished podcast and video audio is mastered to a consistent listening level.
Long account emails truncate cleanly in Settings, narrow flashcard tabs remain usable, and signed-out Library visits no longer report a false content-loading error.

Reliability

Library search inside every AI creator now uses the same live search as Cmd+K, so newly added sources appear, results stay current, and longer result lists can load beyond the first page.
Video Lectures now preserve narration at its natural recorded pace across Freestyle, Illustrated, Math, Kids, and Short modes, instead of speeding up the voice to force a longer script into a shorter target.
Importing a file by URL now works even when a website has a slightly misconfigured security certificate, the same way your browser does. If the certificate genuinely can't be trusted, you'll get a clear explanation.
Video lectures that hit their AI time limit near the end of generation are now reported accurately and retried when possible, instead of failing as an unexpected error.
PowerPoint previews now show a clean, scrollable deck with no editing, sharing, comments, or notes controls. Every slide fits the preview panel in both light and dark mode.

August 6th, 2026

Reliability

Study guides and other AI documents now retry automatically when generation has a temporary startup problem, instead of ending the creation immediately.
Flashcard read-aloud now starts reliably in Safari instead of downloading the audio into a silent player.
Changing a page heading into a paragraph now updates the block immediately and remains correct after reloading; selected text and selected blocks can also be deleted normally.
Word and PowerPoint study guides now consistently name the original document, while native spreadsheet files no longer lead to a PDF-only summary page that cannot open them.

Cleaner profile menu

The profile menu no longer repeats team setup or deleted-item shortcuts. Deleted content remains available under Library → Deleted, and profile pictures stay circular when the sidebar narrows.

August 5th, 2026

Reliability

Video Lectures now repair or reject narration that stops mid-sentence before recording begins, so completed videos finish every explanation cleanly.
Short videos restore their original Scholarly art direction and word-for-word paper-strip captions across four distinct, completely still illustrations.
Daily Chat allowances now reset consistently in both Chat and Billing, so an expired limit cannot block a new day's messages while Billing shows unused credits.
Shared flashcard decks now clearly show that autoplay requires sign-in instead of offering a control that cannot play while signed out.

Chat replies that stay perfectly in place

Typed, retried, voice, and Help chat replies now update in place from the first word to the finished answer, so formatting no longer shifts when streaming ends.
Chat replies keep generating when you visit another page and are still live when you return, without requiring a refresh or restart.

August 4th, 2026

Faster creator steps

Customization is now prepared across creation modals when they open, so Next and Back switch steps immediately without a blank pause.

Stop one answer and send the next

Queued chat messages now have Stop & send. It interrupts an outdated response, safely settles any partial answer, and sends your next message without another click.

Deepseek Flash in every model picker

Deepseek Flash is now available for Chat, Research, Slides and documents, Video Lectures, Infographics and Mind Maps, Flashcards, and Podcasts.
It is an efficient, low-cost reasoning option. Because it is text-only, visual source workflows use the text extracted from your material.

Simpler model pickers

Only Auto (Premium) and Auto (Free) stay up front. Manual choices now live under Premium Models and Free Models, without lock or speed icons cluttering the list.

Reliability

Refining an existing flashcard deck works again instead of failing before the request could be sent.
Chat streaming, read-aloud, and flashcard autoplay now keep going if your session briefly expires, without interrupting your work.
Math formulas no longer create nested scroll areas while you move through Chat and other generated content.

More faithful creation and first-run copy

Podcasts now recognize natural instructions such as “two clearly labeled speakers” as a hard two-voice format, so a producer cannot slip into the finished audio.
When you add a source, Scholarly now names it as a Word document, PowerPoint, spreadsheet, or PDF — matching what you selected — instead of calling every page-based file a PDF.
Welcome and pricing copy now speaks to learners, researchers, professionals, and teams instead of assuming every new user is walking to class.
Teams pricing consistently leads with the canonical $45/seat/month price and names $324/seat/year as the separate discounted annual option.

August 3rd, 2026

A voice picker you can actually hear

Choosing a voice now opens a full picker instead of a cramped dropdown: browse all 26 voices, search, and play a short demo of any voice before you commit.
The same picker is used everywhere a voice is chosen — chat settings, voice mode, read-aloud, podcast guest voices, and video narration — so it always looks and works the same.

Chat and AI Creations settings

The Scholarly AI settings tab was split in two. Chat now holds suggestions, auto-play audio, your voice, language, custom instructions, and memories; AI Creations holds custom designs, check-in questions, and autocomplete.
Video and podcast check-in questions can now be turned on or off from settings, not only from the player.

Long podcasts now actually run long

Requesting a 45 or 60-minute podcast now delivers an episode that genuinely fills that time. Long episodes are planned chapter by chapter and written in sections, instead of trailing off around the half-hour mark no matter what you asked for.
Short targets are respected too: an episode that came out far over your requested length is now tightened before the audio is recorded.

A calmer AI Creations tab and podcast page

The AI Creations tab on every source now matches the folder studio: quiet create buttons with color reserved for each creation type's icon, and simpler one-line empty states. The Sources tab got the same treatment.
The podcast page was tidied up: one title instead of two, a cleaner details line, shorter tab names, and calmer chapter visuals.

Reliability

Fixed: the chapter visuals' next and previous arrows could flip to the neighbouring chapter and immediately snap back. Chapter navigation now lands on the chapter you picked — on podcasts and video lectures.
AI Slides now treats explicit source absences as hard constraints across titles and decorative copy, so a deck cannot invent a date, weekday, event, or causal claim that the source says is not provided.
Chat now finds your PowerPoint content on the first question, including speaker notes, instead of saying the original deck is unavailable and waiting for you to rephrase.
Podcast transcripts now repeat the speaker name at every chapter opening, even when the same person also closed the previous chapter.
When an AI creation limit blocks the next step, Next is now visibly and accessibly disabled while the upgrade action remains available.

August 2nd, 2026

Projects

Projects keep the sources, chats, and AI creations for one goal in one workspace, with project instructions that every chat follows.
Chats started inside a project are grounded in that project's material, and anything you create there is filed back into it automatically.
Any folder can become a project in one click, bringing its contents with it.
Move existing chats and content into a project — and back out again — from the row menus in your library, sidebar, and chat list.
Share a project with your team, by email invite, or by link. Recipients get a read-only view of its sources and AI creations, your chats stay private, and public projects are never listed publicly.
Project memory shows what Scholarly has picked up while working inside a project, and lets you retire anything out of date. Those memories are recalled only in that project.
Find projects from Search or Cmd+K, and browse projects and their folders whenever you choose sources for a new creation.
Drop files anywhere on a project to add them to it — PDFs, Word documents, spreadsheets, slides, and video go straight in.

A calmer, simpler sidebar

The sidebar now focuses on navigation: New, Home, Chat, and a new Library link, with one Recent list that mixes your latest content and chats.
Recently Deleted, Changelog, Share Feedback, and Join Discord moved into your profile menu — same features, less clutter.

Simpler creation menus

Timeline, SOP, flowchart, lesson plan, and outline now live inside AI PDF Creator. Pick the document type after adding your sources instead of choosing between separate creators up front.
Spreadsheet and the former AI File Creator are now one Document & File Creator. AI Essay Writer remains a separate creator.

Expert styles, where you actually decide

The expert style cards in every AI creation panel now sit with the other creative choices near the top, instead of below the instruction box at the very bottom. Same styles, same effect — they were just easy to miss down there.
"Number of flashcards" moved out of the preset box into Settings, next to language and model, where the rest of the dials live.

Clearer free media length limits

Free Video Lectures now run up to 2 minutes and free Podcasts up to 5 minutes. The customize step shows these limits up front, with a direct Upgrade link for longer creations.

Reliability

A PowerPoint or Word upload is now called by its own name and type everywhere, not just in chat — in the viewer, Plan with chat, the Sources list, and generated podcasts and video lectures — instead of being labeled as a PDF.
Fixed: podcasts, video plans and the help bot could tell you a PowerPoint's speaker notes were unavailable. They are extracted from your .pptx and kept with the matching slide, and every surface now says so.
The "How was this…?" feedback card now only appears on the page for the thing it is asking about. It no longer follows you onto an unrelated video lecture or slide deck after a background creation finishes.
Timeline plan-limit errors now include a direct upgrade action, and opening the plan options from the limit check before you start clears any older error banner.
A temporary failure while syncing autocomplete usage no longer reduces your remaining allowance until you reload the page.
People viewing a publicly shared page can now export or preview it. Private pages remain blocked from public download links.
The Premium offer shown after leaving checkout is clearer and easier to use again. It keeps the benefit summary, student proof, and monthly or yearly choice together, while the subscribe and dismiss actions stay visible on phones without covering the content.
When a podcast can't be created because its sources couldn't be read — for example a saved web page instead of the real document — the error now names the actual problem with each source and what to do about it, instead of a generic "no usable content" message.
If your Google Drive access has expired or been revoked, chat tools and AI creations now tell you directly to reconnect Google Workspace in Settings instead of failing with a technical error.
Excel workbooks with native charts now open in Scholarly instead of showing a preview error. Unsupported chart artwork is skipped while every populated worksheet remains available, and the original workbook still downloads unchanged.
AI-created spreadsheets now reject cramped wrapped labels and noisy chart labels that repeat the series, category, and value, so dashboard sheets arrive easier to read.
Podcasts now enforce an explicitly requested two-speaker format before audio is synthesized, so a producer voice can no longer slip into a two-person conversation.
New students now see the tools and choose what to study before any pricing prompt. Upgrade suggestions remain available after they have received value or reach a relevant limit.
Upgrade actions consistently say Premium, voice limits clearly distinguish Free from Premium, and converted PowerPoint or Word viewers label the original file type instead of PDF.
Free Study now shows its 10-card question allowance without interrupting the first question, then explains the remaining deck and upgrade path at the relevant study limit.
Workspace pages once again keep the Scholarly logo and breadcrumb separator visible on desktop, making the current page easier to place and Home one click away.

August 1st, 2026

Plan any AI creation with chat

Every AI creator now has a Plan with chat button beside its standard next step. Open the planning composer in place to discuss your sources and shape the result before creating flashcards, quizzes, slides, videos, podcasts, documents, study materials, and more.

Reliability

Fixed: duplicating a page containing a flashcard deck could silently drop cards. If a card's image failed to copy, the whole card went missing from the copy — question and answer text included. Every card now comes through, and a card whose image can't be copied keeps its text.
Fixed: duplicated flashcard decks came back reordered, with every card that had an image moved to the end. Copies now keep the original card order.
Duplicated flashcards now also keep their AI hint and difficulty label instead of losing them in the copy, and their source citation follows the copy — it opens the duplicated PDF or video in your new page rather than pointing back at the original.
When you let a flashcard deck or quiz finish in the background, Home now keeps the finished item on screen with a link straight into it, and your new deck shows up under Jump back in right away — no page refresh needed.
A creator can no longer sit on "Creating your…" forever if we lose track of a generation. It now tells you what happened and hands the page back, instead of leaving a spinner and a stale browser tab title until you reload.
Fixed: the flashcard feedback prompt no longer sits over Next after card five, so longer decks keep advancing normally.
Finished short Video Lectures no longer open a sharing dialog over their tabs, so Summary, Transcript, AI Creations, and Sources remain usable.
Fixed: after you hit the free upload limit, pressing Next in Add content did nothing at all. It now opens your plan options so the limit is actually actionable.
Chat now knows a PowerPoint or Word upload is still your PowerPoint or Word file, not a PDF — including where to find a presentation's speaker notes.
AI creations now recover automatically when a model provider returns a malformed response, retrying or switching to a backup model instead of failing with "An unexpected error occurred."
Connecting Google Drive no longer fails when you spend more than ten minutes on Google's account and permission screens.
Shared chat links with a malformed address now show a clear not-found page instead of a generic error.

July 31st, 2026

One AI PDF creator for any document

The separate SOP, flowchart, lesson plan, and outline creators are now a single AI PDF creator. Add your sources once, then pick the document type in the customize step.
Need something the presets don't cover? Pick "Anything" and describe the document in your own instructions — a briefing, a checklist, meeting minutes — and it gets built to that shape.
Four new document types: cheat sheet, report, case study, and rubric — each source-grounded and written to the same typeset PDF quality as the existing kinds.

New: AI File Creator

A new creator that turns your sources into a downloadable file. Describe what you want and it picks the format to match — an Excel workbook, a CSV table, a JSON export, a Markdown document, or a calendar file — or start from one of those tiles directly. The existing AI Spreadsheet creator is unchanged and is also available as a tile inside the new creator.

Preview Office files directly

Word documents, Excel workbooks, and PowerPoint decks now open in the shared file preview from chat, research, and saved files. New Word and PowerPoint uploads keep their original file for preview and download.
Office files over 25 MB show a clear preview-limit message and a direct download action instead of attempting to load indefinitely.
Fixed: spreadsheets containing an Excel table — including every workbook the AI File Creator produces — reported that the file could not be previewed. They now open normally.
Office previews now match the rest of the app: PowerPoint decks follow light and dark mode, Word pages sit on the app's own surfaces, spreadsheet rows grow to fit wrapped text, and trackpad scrolling no longer runs away or triggers browser back-navigation. Opening a preview also no longer affects text sizing elsewhere in the app.

Clearer yearly pricing on upgrade

The upgrade modal now leads with the monthly equivalent for yearly plans (for example $12/mo), keeps the annual total visible immediately below it, labels the checkout button as yearly with the same monthly equivalent, and consistently calls the individual paid plan Premium.

More faithful, complete study creations

Free practice exams now use at most one question from each prepared flashcard, and every exam entry point shows that honest prepared-pool maximum instead of repeated variants of the same cards.
When you explicitly ask to preserve every source question, every source section must finish successfully before the deck is delivered. Everyday requests to cover a topic broadly keep the normal faster generation path.
Long video-lecture scenes now introduce their teaching points throughout the narration instead of becoming a static slide in the opening seconds.
Short Video Lectures now keep source markers and machine-style identifiers out of narration, preserving the central explanation as natural speech instead of reading document scaffolding aloud.
Research grounded in a linked PDF now draws labeled excerpts from across the document instead of relying only on its opening section.
Source-grounded chat tables now cite every factual cell directly, so each number, date, or quote can be checked in one click.
PowerPoint speaker notes are now kept with their matching slide for chat and AI creations.
Infographics now honor explicit landscape and portrait requests, recognize historical year ranges as timelines, and stop genuinely oversized exhaustive requests before generation with guidance to narrow or split the content.
Podcast expansion now catches near-duplicate chapter content while preserving distinct chapters that happen to share a generic title.

Reliability fixes

Fixed uploads that could fail with a raw "Retry limit exceeded" message. Brief file storage hiccups are now retried automatically instead of ending the upload, and if storage really is busy you get a clear message and the upload retries itself.
Fixed chat turns that could spend every research step and then save a generic error as the answer. Chat now says plainly when a web search comes back empty, and a turn that cannot reach an answer no longer saves a placeholder reply or spends a chat credit.
Chat reasoning and tool actions now stay in their true order while an answer is streaming, including longer Auto conversations that use several rounds of tools.
Charts created in chat now appear as soon as the assistant mentions them, instead of staying hidden.
Selecting text in a chat now keeps the Ask, Copy, and Speak menu beside the selected words, including after scrolling through a long conversation.
Fixed a page editor crash that could begin after using undo or redo, where further typing appeared on screen but was never saved.
Fixed switching from monthly to yearly billing so a billing update arriving at the same moment can no longer roll your renewal date back.
Fixed rare connection errors where a page load or request could fail once with a server error and then work on retry.
Flashcard creation now honors the selected difficulty all the way through generation instead of silently falling back to the default.
Creation flows now wait for image uploads to finish, and AI Creations treats temporary source-loading failures as retryable instead of incorrectly marking the source as unsupported.
The flashcard creation footer now wraps cleanly when a plan-limit message appears, keeping Build a blank deck readable and usable.
Abandoned-checkout recovery now describes what happened accurately and keeps yearly Premium as the primary option instead of switching a yearly shopper to monthly.
Laureate members now see the correct weekly flagship-credit reset guidance and can receive subscriber feedback prompts, while Free users continue to see the right upgrade gates for premium models.
Research preparation and podcasts now handle missing optional content safely, and the welcome-back dialog has a properly announced title for screen readers.

A more reliable page editor

Undoing or redoing text on a page is now saved. Previously the change was applied on screen but never written back, so reloading the page brought the undone text back.
Read-only and shared pages now stay read-only. Previously they could become editable again after interacting with them, and text typed while blocks were selected could be silently discarded.
Signup and other simple pages now load faster because they no longer pull in the page editor they never use.

Mobile

Interactive podcast questions now scroll into view when they appear, and stay open while you tap around the page.
Fixed the flashcard study card on smaller phones — the card controls no longer fall off the bottom of the screen, and long questions are no longer hidden behind the card buttons.
Opening a creation's customization step now shows a loading state instead of a blank sheet, and Google Drive picks scroll properly when you select several files.
"Other Models" now expands inside the model picker on phones instead of opening a panel on top of it, so every model is reachable.
Plan details that used to appear only on hover — like Laureate's weekly credit allowance — are now readable on touch.
Tapping an image to enlarge it now fills the screen instead of opening at half width.
Bigger, easier tap targets across study, exams, saved instructions, sharing and the plan billing toggle.
Blog posts, the file page tabs, search filters and marketing stats now lay out properly on a phone.

July 30th, 2026

Smarter Auto across Scholarly

Auto now uses GPT-5.6 Luna for chat on every plan, with high reasoning effort on Premium and higher for stronger answers. Free chat stays on Luna with its efficient reasoning setting, while AI creators keep their existing automatic models.

Everything made from a source, in one place

Pages, PDFs, videos, AI Meeting Notes, podcasts, research reports, and saved files now have an AI Creations tab with the creation tools that work for that source.
New flashcards, quizzes, podcasts, video lectures, slides, study guides, worksheets, visual documents, essays, and more stay durably connected to the source they came from, including the PDF pages used.
Search and filter a source's creations by study tools, media, or documents, then open any result directly.
Creation shortcuts now live in AI Creations instead of the assistant's empty conversation, keeping chat focused on questions and explanations.
PDFs, videos, and AI Meeting Notes now keep flashcard creation and linked decks inside AI Creations, replacing their redundant standalone Flashcards tabs.
New flashcard decks, generated documents and files, video lectures, and podcasts have a Sources tab that shows the original material used to create them, including PDF page ranges, with a direct path back to each source.

July 29th, 2026

A faster, smarter voice assistant

Scholarly's voice assistant now uses xAI's Grok Voice Think Fast 2. Conversations respond faster, follow complex study requests more reliably, and handle interruptions and tool use more naturally.

Faster navigation between your work and Home

Returning to Home from PDFs, videos, flashcards, podcasts, recordings, research, and shared chats now feels immediate while keeping your sidebar and workspace ready.

July 28th, 2026

The right Auto model when chat creates for you

When AI Chat starts a video lecture, podcast, slides, flashcards, a visual document, or research, it now uses Auto (Free) on Free and Auto (Premium) on paid plans — the same model choice as the creation dialog.

A cleaner model picker

Named AI models now use compact, single-line rows in every picker. Auto (Premium) and Auto (Free) keep their explanations so their behavior stays clear.

Better recovery from brief connection problems

An account left open in an older browser tab no longer crashes while loading after Scholarly updates available AI models.
If a PDF page image upload is interrupted, processing now retries it before starting over from scratch.
Video and audio downloads now retry after a brief connection drop instead of failing immediately.

Choose the AI that writes your podcast

Podcast creation now includes an AI model picker. Free uses Gemini 2.5 Flash; paid plans default to Gemini 3 Flash Preview and can choose either. The selection writes and reviews the transcript only — voices and audio generation stay unchanged.

Podcast names and voices stay in sync

Every podcast speaker now uses the exact name of the Grok voice you hear — for example, Cosmo, Ursa, or Sirius. This applies to the automatic host, guest, and producer as well as a guest voice you choose.

Podcast navigation stays within reach

Interactive questions now have their own counted tab alongside Chapters and Transcript, and longer podcast pages scroll all the way to every panel.

Follow podcasts with chapter slides

Every new podcast now includes a visual companion by default for everyone. Scholarly generates one clean Editorial slide per chapter alongside the audio, then follows the current chapter automatically as you listen. You can turn it off for an audio-only episode.
Previous and Next now switch podcast chapter slides immediately in Safari, even while the audio is paused.

Clearer, interruption-free study tools

Feedback cards no longer cover quiz or exam answers. They stay out of focused study routes and can always be dismissed.
Flashcard quantity options now describe AI-generated counts as targets rather than guarantees, so short sources no longer appear to promise hundreds of useful cards.
AI Slides now reviews pages at a readable size and checks card spacing and complete equations before finishing, reducing overlapping text and missing formulas.
Text fields no longer grab keyboard focus automatically when pages, searches, or study steps open.

A clearer welcome and faster path to studying

The welcome tour now separates its introduction, plan comparison, study tools, and start choices into four focused screens.
Completed flashcard tasks now offer Start studying directly from the completion message and Home task tray.

July 27th, 2026

Fewer generations lost to a single hiccup

Google Drive files that can't be downloaded are now caught when you pick them, instead of failing partway through a generation.
PDFs now open reliably in the in-app reader instead of failing while the viewer is still loading.

Clearer, more honest error messages

When a document has no lesson content, we no longer suggest saving it as a PDF again — we point you to the pages or link that do have the material.
A Drive file whose owner turned off downloading now explains that and how to fix it, instead of asking you to reconnect an account that was working.

A cleaner, context-aware upgrade screen

Opening plan options from an Upgrade Plan button no longer shows a limit warning just because the account has used free credits. Limit warnings now stay attached to the action that actually reached the limit.
The upgrade dialog no longer shows a bright outline around the entire window when keyboard focus moves into it. Buttons and fields keep their normal visible focus indicators.

Safer defaults and more faithful creations

Every AI creation now starts in your saved language, using your browser locale with an English fallback the first time. Changing Language in any creator updates that account preference everywhere.
AI Slides now preserve source values and units exactly. When a table is too dense, it leaves out a column instead of inventing summaries, ranges, or units.
The welcome tour can now be skipped from its first screen and dismissed with the Escape key.

Honest, broader practice-exam coverage

Exam mode now shows how many of your deck's cards actually have practice questions — "N of M cards prepared" — instead of promising questions that were never generated.
On paid plans, creating an exam now fills only the missing practice variants needed for that exam's size, so paid exams are no longer restricted to a stale 10-card pool.
Free decks show the 10-card preparation limit right where you pick an exam, with the upgrade path next to it.

Video lectures grounded in your source again

Prepared video lectures can once again look at the PDF pages that have figures, tables, or equations, so those details make it into the lecture.
Video lectures can now show concise on-screen cards instead of repeating the narration; scenes without cards still use the existing narration-based text.

Bug fixes

The cancel-flow pause offer now matches the 3-month pause you can set yourself in billing settings — it was previously capped at 2.
If you cancelled because you did not want auto-renewal, the follow-up email no longer offers a discounted subscription; it offers a plain restart instead.
Win-back discount codes could expire before paid access ended. Their expiry is now anchored to remain valid for 21 days after access ends.

July 26th, 2026

One consistent Premium plan name

Same plan, same price, same features — Scholarly's paid plan is now called Premium everywhere in the product. Nothing changes about your subscription or billing.

Flagship AI credits for Scholarly Laureate

Laureate includes 2,000 weekly credits for flagship-model work. Standard and advanced models stay unlimited on both Premium and Laureate, so Premium access is unchanged.
Laureate members can see their weekly flagship-credit balance, usage details, and reset time in Settings → Usage.
Laureate members can top up flagship credits in a heavy week without changing plans.

Your work stays where you left it

A PDF or video now shows the flashcard deck made from it, instead of an empty tab offering to create one you already have.
"Jump back in" on the home page now includes your flashcard decks, not just the file you made them from.
The free-limits banner no longer appears while your first creation is still generating — it waits until your work is ready.
The chat limit now tells you when it resets, so a daily limit no longer reads as a permanent one.
Finishing a creation no longer flashes the create form back up with a "Retry" button while it opens your new content.

More faithful study materials

PDF and video summaries now follow the language of your source by default instead of forcing English.
LaTeX formulas in flashcards and study questions no longer lose commands such as fractions, Greek letters, or text labels during generation.
When an AI creation cannot read every PDF page in one go, it is now told exactly which pages were skipped so it can continue reading them instead of silently missing part of the source.
Flashcards now stop when only a link or reference to missing material arrives, rather than inventing a confident-looking deck from general knowledge.
AI podcasts now keep a direct, appropriate tone for sensitive human topics instead of forcing cosmic metaphors into every subject.
Infographics no longer risk printing internal layout labels such as “TITLE” or “SECTION” onto the finished poster.

Scholarly for Teams, easier to find and start

Teams is now a full plan on the pricing page, alongside Free and Premium, with per-seat pricing that follows the monthly/yearly toggle.
Team setup is now reachable from the profile menu, billing settings, and plan options — and those entry points open team setup directly instead of sending you to a marketing page.
If you sign up or use Scholarly with a work or school email, signup and your home page now mention Teams — one plan and one bill for everyone — instead of the generic pitch.
"Talk to sales" on the Teams page is now a form on the page itself, so enquiries reach us without needing a mail client.
The Teams page now leads with turning your organization's existing handbooks, recordings, and decks into onboarding and training content.

Fewer generations lost to avoidable failures

You can now make a video lecture from a short topic — paste “Krebs cycle” and it generates, instead of being turned away for being too short.
If an AI provider declines to read a document on content-safety grounds, we now try a different provider automatically. Legitimate medical, anatomy, and clinical material no longer dead-ends.
A PDF with nothing readable in it now says so straight away, instead of showing “still processing” for ten minutes and then failing.
Picking a Google Drive file that is over your plan's size limit is now flagged the moment you choose it, with the upgrade path shown — rather than failing after you press Create.
A video lecture whose picture ran out before the narration finished is now caught and re-stitched while it is still being made, instead of failing at the very end after several minutes of work.
If an AI provider declines to read your source while preparing a podcast, we now try a different provider before giving up — the same recovery study guides already had.

Bug fixes

Switching an existing monthly subscription to yearly billing failed every time with a generic "please try again" message. It now goes through.
Some new accounts were dropped onto the home page instead of onboarding right after signing up, and could end up marked as onboarded without ever seeing it.
If our servers hiccuped in the moment right after you signed in, you could be sent straight back to the login form even though your sign-in had worked.
An empty response from the server could sign you out mid-session even though your session was still valid.
A failed page navigation could reload the app and silently discard an edit that was still being saved. Reloads now only happen when a new version of the app is available.
Opening scholarly.so/content directly showed a "Page not found" error instead of your library.
Reloading a podcast part-way through no longer re-asks the questions you had already answered while listening.
Videos whose file was structurally damaged could still be delivered and then refuse to play in the browser. They are now caught during generation and rebuilt.
Video generation could stall for around 20 minutes before recovering, even when the next step was already done. It now continues as soon as that step finishes.
Explore search now retries when results are briefly unavailable, instead of falling back to a weaker match.
A request that was in progress during a brief outage is now allowed to finish instead of being cut off.
Opening a dialog now moves keyboard focus into it, and closing one returns focus to whatever opened it. Focus used to stay on the page behind, which left keyboard and screen-reader users outside the dialog that had just taken over the screen.
Pressing Enter in the email field on signup now moves to the password field. It previously did nothing at all.
Video lecture title and closing cards no longer print an internal authoring note as on-screen text, and on-screen lines are no longer cut off mid-sentence when the card still had room for them.
The “NEW” badge on the home page was too light to read comfortably in light mode.
Compact library rows painted the same colour as the page behind them; they now read as distinct cards.
Help and marketing pages listed slide themes that are no longer offered.
The screen where you choose what to make announced “Your content is ready!” before your file had been uploaded. It now names the step instead of claiming your source is already saved.
The monthly and yearly options in the upgrade dialog can now be moved between with the arrow keys, the way a set of radio buttons is expected to work.
Podcast instructions that name which hosts should appear are now followed, instead of the standard three-host cast being used regardless.
Video generation could throw away a nearly-finished lecture and start over after a step briefly misbehaved, even though it had already corrected itself — adding several minutes for no benefit.
Audio and video that would not play blamed an expired link and told you to refresh. Nothing expires, and refreshing never helped; the message now says what actually happened.
Help lists and navigation no longer pause unexpectedly or reload the page you were reading.

July 25th, 2026

Smarter defaults and clearer dialogs

AI Chat and creation dialogs now offer Auto (Premium) and Auto (Free), so you can let Scholarly use the recommended model for the quality tier you choose.
Voice-picker search now uses one clean, consistent surface in both light and dark mode.
Plan options now show a yellow limit explanation only when the action that opened them actually reached that limit.
Locked Full HD and custom-length video options now explain exactly what Premium unlocks before showing plan choices.
Welcome tours now introduce what Scholarly can do before showing the option to skip the rest.

Video lectures show your numbers, not placeholders

Chart, equation and statistic scenes in an AI Video Lecture now use the real figures from your source. Previously these could fall back to placeholder scaffolding — a generic two-bar chart or the scene's own title typeset as an equation — even while the narration read your actual values.
When a scene genuinely has no figure worth showing, it now renders as a clean text callout instead of an empty or invented visual.

Podcasts

New podcasts now come with interactive questions. While you listen, a quick check-for-understanding question appears right after the idea it tests finishes — and never pauses the audio.
Answer to get an explanation grounded in the episode, revisit any question from the episode's question list, and track your score across attempts. You can switch questions off from the player at any time.

Exams and quiz limits

The Exam tab now prepares its own study questions instead of waiting on the Questions tab, so exams open on a deck you have not quizzed yet. If questions cannot be prepared, you get a clear message and a Try again button rather than an endless spinner.
Returning to a deck after using your daily practice questions now shows the full limit screen — questions remaining, when it resets, and a way back to your flashcards — instead of a bare notice.

Interface fixes

The upgrade dialog now scrolls your selected plan into view on short screens, so the highlighted term always matches the price on the button.
On phones, the chat box on Home no longer overlaps its own buttons, so tapping anywhere in the field starts typing.
The “How was this?” card after a generation no longer sits on top of the chat send button.
Copying a share link from a private item now says up front that it will make the item viewable, instead of only telling you afterwards.
Home creation shortcuts are back to the roomier three-card layout, with full AI tool names and the original quick-access order.
If Google's permission screen closes without the Google Drive box ticked, Scholarly now tells you which box to tick and offers Try again on the spot — instead of a message that disappeared and left no way to retry.

July 24th, 2026

Teams for training, onboarding, and sales

New Teams marketing pages for employee training, employee onboarding, sales enablement, and businesses — plus help docs for getting started, billing, sharing with Your team, and switching from an individual plan.
Expanded Teams help covers seats ($45/seat/month or $324/seat/year), Premium usage and limits, and the shared library workflow for L&D and research groups.
New ChatGPT Business (formerly Team) comparison and guides for buyers evaluating AI employee training tools and sales enablement from company docs.

Clearer study-tool guides and comparisons

Updated PDF Summarizer, flashcard, homework-helper, Quizlet, and Chegg pages with clearer comparisons, examples, and more accessible imagery.

Chat attachments stay with the right message

Images and other attachments sent with your first chat message now stay on that message instead of jumping onto the next one.
Attaching multiple images in chat now shows a compact equal-height grid (up to four) instead of stacking large previews in a tall list.
Fresh web searches in AI Chat now return current sources again instead of failing when the search service rejects the request.
Chat replies no longer fail permanently when one AI model rejects a long conversation — the message now moves to another model instead of leaving the conversation stuck.
The chat model picker now highlights four recommended choices, making it faster to choose a capable model without scanning a long shortlist.

Video lectures and research recover instead of failing

Video lectures and research that were interrupted mid-generation now retry automatically instead of failing and refunding.
A video whose final render fails a quality check now regenerates once automatically, and a video ending moments before its narration is repaired in place instead of rejected.
Long video lectures no longer stop early against a limit that was smaller than the work they were approved to do.
PDF study guides no longer fail, or get cut short partway through, on longer documents.
Flashcard sets from dense sources now switch to a working model in minutes instead of retrying until the time limit, so decks arrive far sooner.
Video lectures now catch a corrupted or silent render while the video can still be rebuilt, instead of failing at the very end.
A video lecture that got stuck retrying the same failed step now gets a clear correction and, if it still cannot move on, is retried automatically instead of quietly using up the whole generation.
Videos, podcasts, flashcards, and other AI-created study materials no longer fail just because the model produced slightly more text than requested.

You stay signed in through brief outages

A temporary connection or server error while loading your account no longer signs you out and sends you back to the login screen.

More reliable creation from your sources

Recording and transcription no longer use an AI creation, leaving your included creation available for the flashcards or quiz you make from the recording.
When one source fails while creating Flashcards or a Quiz, successfully uploaded sources stay ready and the failed source can be removed without starting over.
Creation dialogs now keep clear limit guidance and an Upgrade action visible when a server-side plan limit is reached.
Post-purchase tools and cancellation guidance now keep the record of features you have tried after your account refreshes.
Signing up from a tool page now carries that tool into onboarding and opens the matching creation flow, so you can continue without starting over.
The welcome tour now introduces upgrading earlier, restoring the step order that helped more new users reach the plan explanation.
Slide creation no longer gets stuck repairing harmless text overlap, and Very High flashcard sets once again target at least 200 useful cards when the source supports it.
If Essay Writer generation is interrupted after claiming a refund, the system now reconciles it so the AI creation credit is returned.
Google Drive searches for large or shared study materials now read every result page and use the file details those filters need.

Clearer billing choices

After a successful payment or plan change, your active plan now appears immediately instead of briefly showing the old plan or asking you to retry checkout.
The plan chooser can now start with monthly billing selected, making the lower-commitment option easier to continue with while yearly savings stay visible.
Monthly members see the yearly-switch reminder near renewal, at most once per billing cycle.
If you leave a yearly checkout, the recovery screen now leads with monthly billing instead of immediately repeating the yearly offer.

Smoother dialogs

Dialogs no longer pre-select Close, Skip, or another button as soon as they open, removing the unexpected blue outline around those controls.
Creation settings now sit in their own labelled section, separate from the design choice, with each option on its own row so the setup is easier to scan.

A much better phone experience

Fixed screens where the main button could end up off-screen on a phone: the post-upload "what to create" chooser, the post-purchase welcome steps, the checkout offer, and the practice exam setup now keep their primary action reachable.
Long flashcard answers, quiz questions, and the end-of-session summary no longer get cut off with no way to scroll to them, and long multiple-choice options are shown in full instead of being truncated.
Plan and competitor comparison tables now stack into readable cards on phones instead of squeezing three columns into a sideways-scrolling strip — and the explanations that were previously hover-only are shown inline.
Video, recording, and PDF pages now show the item's name on phones, including when you open a shared link.
Hitting your AI creation limit now shows the upgrade options instead of the create buttons silently doing nothing, and the "finish yearly checkout" reminder no longer covers the chat box or recording controls.

July 23rd, 2026

Reliability fixes

Long, tool-heavy AI Chat conversations now keep your latest message intact instead of occasionally failing before the answer starts.
Large PDF summaries now finish reliably instead of occasionally failing near the end.
Healthy long video lectures are no longer rejected when export creates a harmless sub-second difference between audio and video timestamps.
Team workspaces now load more reliably, reducing occasional account-loading failures when many people are signing in at once.

A clearer refund policy

The refund policy now explains that most requests made within 30 days are approved, while unusually extensive use, fraud, or abuse may require a case-by-case review.

July 22nd, 2026

More room to shape your AI

Custom instructions now allow up to 5,000 characters across Chat, Skills, Custom Designs, and every supported create flow.
Plus and Premium members can now choose Claude Sonnet 5 for AI Video Lectures.

Short-form video, made more reliable

Kids & Story is now the landscape twin of Short: a short-form, full-width illustrated story with crisp cuts, paper-strip captions, and the same logo controls.
Video modes now check that narration and visuals describe the same chapters before an export can finish.
Large and scanned sources are processed in small, resumable batches, so a brief interruption no longer throws away completed video preparation.

Creating and upgrading

AI Study Guide is easier to find on Home and after uploads, while Worksheet now lives under More in a balanced action grid.
Generated and edited page titles no longer revert to Untitled when you leave the editor.
Plan dialogs now show the true reason they opened and support complete Tab and Shift+Tab keyboard navigation.
Large textbooks and PDFs now finish processing much faster, so you can start studying sooner.
Large PDFs now open incrementally and stay responsive while you scroll or zoom, without downloading and rendering the entire document up front.

July 21st, 2026

New Gemini models

Gemini 3.6 Flash and Gemini 3.5 Flash Lite are now available across Chat, Research, Slides, Video Lectures, Infographics, Mind Maps, and Flashcards.
If a retired model was selected, Scholarly now chooses the current default for that feature instead of silently pretending it is a different named model.

Clearer plans and recovery

Yearly and monthly checkout options once again show the exact charge up front — including $144 today or $30/month — with a direct monthly choice.
Returning from checkout now shows the file, action, or limit that led you there and lets you pick up where you left off.
Upload and AI limits stay visible on Home, Chat, and page upload surfaces with accurate reset or lifetime wording and a persistent upgrade action.

Your source survives the whole create flow

Files are saved before customization or checkout can navigate away, so returning to the library no longer loses an upload that was ready to create from.
Practice Exams in Auto language now follow the main language of the source instead of being overridden by a small translated glossary.

July 20th, 2026

Scholarly for Teams now starts at one seat

You can create a full Teams workspace for one person and add teammates later; the 29-seat self-serve maximum is unchanged.

A refreshed Help Center

A new Memory guide explains how the AI Assistant saves useful facts, how to add memories yourself, and how to mark them outdated or restore them.
Every Help Center article was checked against the current product, with outdated model, plan, workflow, and feature details corrected.

Fixes and reliability

Chat keeps generating when a phone locks or a connection drops, then reconnects quietly; Stop is now an explicit action instead of an accidental disconnect.
Emoji in Word, PowerPoint, and other Office files now render visibly in converted PDFs instead of disappearing.
Clearing the email field on login no longer silently clears or desynchronizes the password field.
Podcasts, recordings, and Deep Research now show clear Processing or Failed states across Home, libraries, and search.

July 19th, 2026

Mind Maps with real, readable text

Mind Maps now render as crisp PDFs with exact labels, so their text stays searchable, selectable, and easy to read.

More resilient AI generation

Podcasts now save completed chapter audio and retry through temporary voice-provider outages instead of discarding the whole episode.
Video Lecture narration is synthesized as one continuous performance whenever possible, removing the repeated speed and tone reset at every chapter.
Flashcards can now read browser-printed PDFs from their page images when the selectable text contains only headers, dates, and URLs.

Fixes

Email signup or login now offers a real Continue with Google button when the address already belongs to a Google-linked Scholarly account.
Branded Short videos now include a crisp Scholarly mark, while paid no-logo exports stay watermark-free.

July 18th, 2026

Smoother AI Chat

New answer text fades in smoothly, citations appear as source badges while the answer is still streaming, and the finished response no longer snaps into a different layout.

Flashcard exports you can actually reach

Export and Daily Goal now open with a click or tap, making PDF, Print, and Anki export available on both desktop and touch screens.

Podcast reliability

Podcasts recover from temporary transcript and voice-generation failures with bounded retries instead of failing the whole episode on the first provider hiccup.
Older podcast setups with a missing guest name now safely use “Guest” instead of crashing during transcript creation.

A clearer yearly option

Monthly subscribers who cancel because of price can switch to yearly billing inside the cancellation flow, with the full charge shown before confirmation.

July 17th, 2026

Illustrated video lectures

Video Lectures have a new Illustrated design: a full-length, hand-drawn explainer where one quirky character sketches every idea on a clean white board.
Each scene turns one idea into a simple visual metaphor — a coin ramp, a growing jar, a balance scale — with its handwritten labels drawn right into the art.
Both Illustrated and Short now hold each scene as a clean still with crisp cuts, instead of a slow zoom.

Short videos

Video Lectures have a new Short design: a vertical (9:16) short video that distills your source into one tight, illustrated story.
The narration appears on screen word-for-word as paper-strip subtitles, synced to the voice — Shorts work with the sound off.
Every Short is art-directed in one of four Scholarly styles — cobalt dither, oil painting, papercraft diorama, or sketchbook journal.
The video player now shapes itself to vertical videos instead of adding black bars.

July 16th, 2026

Fixes & improvements

Video lectures now automatically retry on a different AI model when a provider has a temporary problem, instead of failing your generation.
Video lectures that run past their generation time limit now automatically retry once on a different AI model instead of failing and refunding your credit.
Flashcard study questions no longer disappear when the AI skips a card — the deck keeps every question it generated and fills in the rest the next time you open study mode.
PDF summary errors now show a clear, friendly message instead of technical error text.

July 14th, 2026

New — choose your voice across Scholarly

Scholarly now includes 26 official multilingual Grok voices: 21 new voices plus Ara, Eve, Leo, Rex, and Sal, available for AI Video Lectures, AI Podcasts, read-aloud, and live Voice Mode.
Choose the exact voice for live Voice Mode and read-aloud in Scholarly AI settings, choose a podcast guest voice, or choose the narrator for a video. Each option explains its tone.
Luna — a gentle, patient voice — is the new default for live Voice Mode and read-aloud. For podcasts and videos, leave voice selection on Auto and Scholarly will choose voices that fit your material.
Voice Mode now handles reconnects and interruptions more reliably, without overlapping old audio or losing a turn that still needs to be saved.

Bug Fixes

Fixed a crash that could close the page while an AI answer was streaming. Answers that mixed a plain “*” with a math formula — like “5 * 3” next to \times — could take down chat, PDF, and flashcard pages mid-response. They now render correctly.

July 12th, 2026

Bug Fixes

Fixed a rare error that could stop the Home page from loading for some workspace members.
Keyboard shortcuts (including ⌘/Ctrl + K search) no longer occasionally error on Safari when a password manager or browser autofill fills in a field.

July 11th, 2026

Bug Fixes

Copying a share link now works reliably on Safari and iPhone/iPad — tapping “Copy share link” no longer fails with “Couldn't copy the link.”
Flashcard generation no longer dead-ends with “try different files” when the AI returns a response our checker can't read — we now automatically retry on a second model instead of failing the whole deck.

July 9th, 2026

Improvements

Sidebar layout refreshed: Home, Chat, and Recently Deleted sit at the top; a primary New button and search sit below; Content / Chats tabs filter Recent, Folders, and chats. Recent and Pinned now use the same type-colored rows as Home, and dark-mode sidebar text is easier to read.

July 8th, 2026

Bug Fixes

AI Video Lectures that stall while planning now show a clearer message and retry on a stronger model instead of failing as a vague “technical issue.”
Flashcard creation no longer dead-ends after a brief AI hiccup with “try different files” — we now retry automatically when the model returns an incomplete or unreadable response.
Fixed sign-up occasionally crashing when finishing the last registration step after Google sign-in.

Improvements

Grok 4.5 from xAI is now available (replacing Grok 4.3) across chat and create tools. On paid plans it is the default model for AI Video Lectures, AI Slides, Infographics, Flashcards, and Research (free stays on DeepSeek). Previous Grok 4.3 selections continue to work automatically.
Refined the yearly Premium savings banner on Home so the discount and switch-to-yearly offer are easier to scan.
Tightened spacing on the Create-with-AI option grid so longer titles like “AI Video Lecture” fit without being cut off.
Removed the rotating study tips from creation loading screens — just the status and progress now.
Fixed design/style option cards in create modals flashing a light white hover in dark mode.
Simplified the create-modal “close while generating” button to a clear Close action (no more “continue studying” wording).
The “More credits” model badge (e.g. on Claude Sonnet 5) now only appears for team/enterprise accounts that use weekly credits — not on individual plans.
Grok 4.5 in AI Chat always thinks before answering, so chats no longer fail if thinking had been turned off.
Fixed a chat bug where your message could disappear after a failed reply even though it was saved — the original text stays visible for retry.

July 7th, 2026

Bug Fixes

AI video lectures now work from photos and scanned documents. Previously, creating a video from an image or an image-only PDF could fail with an unhelpful message telling you to pick a different model — now we automatically read your images and build the video.
Fixed AI Flowcharts where the steps could render as solid black boxes that hid their labels — every step now shows as a clean, readable box with its text clearly visible.

Improvements

Cleaned up the sidebar. A prominent New button and search sit at the top, with Content and Chats sections for browsing your library, folders, and recent chats.

July 6th, 2026

Bug Fixes

Flashcards no longer fail on a brief AI hiccup — if the model returns an empty response, we now retry automatically (and fall back to a backup model) instead of failing your deck and using up a creation.
Fixed a rare issue where creating flashcards could fail with an error or get stuck partway — even when your cards had already been generated. Flashcard creation now reliably saves your finished deck.
Clearer message when an AI video lecture source has too little text — instead of wrongly suggesting your file is scanned or telling you to “run OCR,” we now simply say the source is too short and to add more detail.

Improvements

Tidied mobile sign-up/login forms and fixed a rare Google sign-up crash.

July 5th, 2026

A cleaner AI Meeting Notes page

A slimmer, more elegant player — the bulky playback panel is now a single, compact bar, so your transcript, summary, and tasks get more room and the whole page feels calmer.
Easier to read — refreshed the layout with more breathing room around your transcript, summary, and action items.

Improvements

Chat now quietly rides out brief hiccups from the AI provider — if a response can’t start because the model is momentarily overloaded, we retry automatically instead of showing an error.
Signup starts you in the free workspace — the final “How will you use Scholarly?” step now always pre-selects the free “Just me” option, so tapping Continue takes individuals straight into their personal study space. The paid Teams option stays one tap away, just never pre-picked.
Share entire folders — folders can now be shared just like any other item. Recipients get a read-only view of everything inside, and folders shared with “Your team” show up in your team’s shared library automatically.

Bug Fixes

Clearer messages when flashcards can’t be created — if you paste a short topic or upload a photo with no lesson content, we now explain what to do for that kind of input instead of showing PDF-only advice about “pages” and “Print to PDF.”

July 4th, 2026

Introducing Scholarly for Teams

One workspace for your whole group — put a class, department, research lab, school, or company on a single plan. Every member gets the team’s chosen Premium or Laureate access and works from your shared material.
Choose Premium or Laureate — every seat inherits that plan’s models, features, and limits, with admin controls for the model tiers the team can use.
Per-member usage, without a team wallet — each person uses the limits included with the chosen plan, so there is no shared balance to divide or watch count down.
Admin controls in one place — invite by email or link, Member and Admin roles, shared source libraries, and one central bill. See Scholarly for Teams to start a team.

AI Image Playground upgrades

High-quality mode — a new Quality selector lets paid plans generate sharper 2K images on models that support it, and shows exactly which models will use it.
See which model is generating — while images render (and if one fails), each tile now shows the model producing it, so comparing models side by side is much easier.
Removed the Style menu — describe the look you want directly in your prompt instead.
Deleting an image now asks for confirmation first.
Fixed the remaining-generations counter showing “Infinity free left” on unlimited plans.

AI now reads your PDF pages the way you see them

Generations grounded in the actual pages — when building slides, study guides, worksheets, videos, and other content from a PDF, the AI now reads the relevant pages as full page images by default, so diagrams, equations, tables, and handwriting are read exactly as they appear instead of relying on extracted text that can drop or garble them.
Infographics and mind maps see your pages too — they now look at your PDF’s actual pages when planning, so visual material like charts and diagrams makes it into the result.

A cleaner, more consistent look across the app

Light mode got a big polish pass — hundreds of panels, cards, and labels across chat, recordings, podcasts, flashcards, settings, and more now have proper contrast, so nothing looks washed out or blends into the page.
Dark mode fixes everywhere — missing dark styles on hover states, cards, and text were filled in across the app, and equations in the page editor no longer render as white strips in dark mode.

Improvements

Print your PDFs and slides — the three-dots menu on PDF and slide viewers now has a Print option that opens your browser’s print dialog with the document ready to go.
Pasting a link no longer uses up your free file upload — links you add as sources are treated as sources, not file uploads, so your lifetime upload credit stays available for real files.
Added a Skip option to the welcome tour so you can jump straight into the app.

Bug Fixes

Quiz and exam questions now test understanding, not diagram trivia — questions built from your material no longer ask you to recall an exact value or timing read off a source’s illustrative graph (like “at what time does the curve peak?”). They now focus on the mechanism and relationships the figure is showing.
Fixed upgrading being blocked for some users — clicking an upgrade button could show “An error occurred while creating the checkout session” instead of opening the checkout page. Checkout now opens reliably, and we’ve added extra safeguards so this class of problem can’t block a purchase again.
Fixed Home and All Content sometimes reloading more of your library than needed when switching views or filters, so large libraries stay faster and smoother.
Fixed the welcome guide overstating how many free AI creations some accounts include — it now always matches your actual allowance.
Fixed pacing markers like “[slow]” occasionally appearing in AI video lecture transcripts.
Clearer help when a PDF is really just a printed document-viewer page — if you upload a “Print to PDF” of an online document viewer (SharePoint, OneDrive, or Google Docs) that was saved before the document finished loading, the file only contains the page’s web address and a page number, not the actual document. We now spot this instantly and point you to download the original file — across flashcards, quizzes, podcasts, slides, and AI videos — instead of trying for a while and then showing a confusing error.
The Print button on the Formula Sheet Generator now works everywhere — it reliably prints just your formula sheet (not the whole page), and if your browser blocks the print window it downloads the sheet for you instead of showing an error. This fixes it on iPad and iOS, where printing used to dead-end.
Fixed the billing and connections pages showing a bright white background for dark-mode users.
Fixed chart labels in flashcard statistics being nearly unreadable in dark mode.
Fixed several menus and drawers feeling sluggish when opening — they now respond instantly.
Fixed the “last viewed” time on shared content showing an older visit instead of the most recent one.

July 3rd, 2026

Custom Designs are now free for everyone

Save your own look and reuse it — on any plan — create a custom design (your style instructions plus reference images) and apply it when generating Slides, Story Books, Infographics, Mindmaps, and AI Videos. It used to be a premium-only feature; now everyone can build and use them.

Improvements

Your most-used dialogs now open instantly — Upload Content, flashcard and quiz creation, the welcome tour, and the plans dialog no longer pause for a moment the first time you open them.
Your folder’s name now shows on your phone — opening a folder on mobile now displays its name at the top, so you always know which folder you’re working in.
Deleting a custom design now asks you to confirm — removing a saved design used to happen on a single tap, which was easy to trigger by accident. We now show a quick confirmation first, so you won’t lose a saved look and its reference images by mistake.

Bug Fixes

You can now remove reference images in Custom Designs on your phone — the remove (×) button on a reference image was only visible on hover, so it couldn’t be tapped on a touchscreen. It’s now always visible on mobile, and the Save / Back buttons stack neatly instead of crowding one line.
Saved web pages now work as study material — if you add a saved web page (for example a Google Drive or Google Docs viewer page) as a source, we now pull out its readable text automatically instead of failing. When a page is really just a sign-in or viewer shell with no content, we tell you right away to download the actual file — instead of trying and failing a minute later.

July 2nd, 2026

Voice Input in Chat

Speak your message instead of typing it — there’s a new microphone button next to Send in AI Chat. Tap it and the input turns into a live recorder with a waveform that moves as you talk; tap stop and your words are transcribed straight into the message box, ready to edit or send.

Improvements

A proper welcome on your phone — new sign-ups on mobile now get a quick, phone-friendly setup: pick what you want to make (flashcards, an AI video lecture, a quiz, or a study guide), then snap a photo of your notes, choose a file, or paste text — and Scholarly starts building it right away. Previously, phones skipped the welcome tour entirely.

Help Center

A full refresh of every help guide — all 58 articles were checked against the current product, and 37 were updated so what you read matches what you see: the new model picker, PDF page selection in every create flow, typeset document themes, AI Meeting Notes, Deep Research file deliverables, and current video modes and lengths.
Four new guides: Paste Text (turn pasted notes into study material), Studying from YouTube Videos, Deleting & Restoring Content, and Account, Login & Password Recovery.
Removed outdated information across help and product pages — including references to a free trial that no longer exists and features that have been retired.

Bug Fixes

Scanned PDFs from Google Drive now work for flashcards — a scanned or image-only PDF picked from Google Drive used to fail with a “blank or unreadable” error even when it was full of content. We now read its pages as images (the same way uploaded scans already work), so it generates cards normally.
Clearer messages when a source can’t be read — if your Google Drive connection has expired you’re now told to reconnect it (instead of a generic “try again”), and empty files or not-yet-transcribed videos now explain exactly what to fix — across AI video lectures, slides, study guides, infographics, and podcasts. These cases also stop retrying pointlessly and refund your credit right away.
YouTube videos no longer fail with a “no transcript” error when building an AI Video Lecture or Podcast — some videos (most often long ones) could report no transcript even though captions were available. Scholarly now recovers the transcript automatically, so generation just works without needing to open the video first.
Fixed the billing link in payment and renewal emails — the “billing settings” link in the payment-failed and yearly-renewal emails pointed to a page that didn’t exist. It now takes you straight to your billing settings.

July 1st, 2026

Improvements

Paste Text is now a first-class way to add study material — a new Paste Text option on Home and a Paste text tab in the Add content dialog turn your pasted notes, lecture transcripts, or articles into a saved source you can study from, no file needed.
Made it clearer that YouTube links are supported: the Upload Content tile now says so, and the Add content dialog highlights YouTube in its link section.
Moved Study Guide to the front of the Home create row.
Tidied up the Home page create options: the newest AI agents — AI Timeline, AI SOP, AI Flowchart, AI Lesson Plan, and AI Outline — now live under the More menu along with the AI Image Playground, keeping the main row focused while every tool stays one click away.
Added a quick Folder shortcut and surfaced AI Chat in the Home create options, and moved Practice Exam into the More menu.
Gave the Add content dialog more comfortable side spacing on mobile, so content no longer hugs the screen edges.
Folders can now be renamed from the folder page — click the folder’s name (or the pencil icon next to it) in the header to edit it in place, just like renaming a PDF or flashcard deck. You can also generate a title with AI while editing.
Redesigned the chat model picker: a focused Recommended Models list up top, with everything else tucked into a dedicated Other Models menu instead of expanding the same list — plus a full-color Gemini logo.

Bug Fixes

Fixed AI Video Lectures coming back in English when your source material was in another language — with language set to Auto, the video now matches your source’s language (Spanish notes make a Spanish video). Picking a specific language still works as before.
AI Video Lectures now make fuller use of their runtime on dense sources instead of over-compressing, stay closer to your material (no invented facts), and preserve your own script’s wording when you provide one in the instructions.
Fixed the Custom Designs editor’s create button staying silently disabled — it now tells you what’s missing, and the design picker shows upfront that custom designs are a Premium feature.
Flashcards now work with scanned or photographed PDFs from Google Drive. If a PDF has no selectable text, Scholarly reads its pages as images instead of stopping — so a scanned textbook still turns into a full deck.
Fixed chat citations sometimes showing as raw source codes instead of clickable source badges — source links now render correctly on every chat model.
Citations now appear as clickable source badges while the answer is still streaming — previously they showed as raw citation text until the response finished.
Fixed AI Video Lecture captions appearing as huge paragraph blocks instead of readable subtitle lines.
Fixed the Build Flashcards button appearing off-center in the practice exam “What would you like to study?” empty state.
Fixed the model picker in chat not showing a hover highlight in dark mode.
Fixed Claude Sonnet 5 erroring out when Thinking was turned on in chat — it now thinks and answers normally.
A model’s thinking summary now appears above its answer instead of below it.