Uploading Content

Everything in Scholarly starts with your materials. Upload PDFs, documents, images, audio files, or paste URLs to get started. The platform processes your content and makes it available for AI chat, flashcard generation, quizzes, podcasts, video lectures, and more.

How to Upload

There are several ways to get content into Scholarly:

• Drag and drop: Drag any file onto the page from your computer. A drop zone appears to confirm the upload.
• Upload button: Click the upload button on the home page or in the sidebar to open the file picker.
• Paste text: Choose Paste text from the control at the top of the Add content window to paste notes, a transcript, or an article. It becomes a source just like a file. See Paste Text.
• Paste a URL: In the upload modal, paste a website URL or YouTube video link. Scholarly extracts the content automatically.
• Google Drive: Pick files straight from Google Drive without downloading and re-uploading them. Choose Google Drive in any create window, in AI chat, or in Deep Research. See Connections for the supported Drive file types and how to connect.
• From chat: Attach files directly in the AI chat input by clicking the attachment button.
• On your phone: Add content opens as a sheet: Cancel and the title in a bar at the top, then rows for Take Photo, Photo Library, and Choose Files, with your plan's size limit as a footnote. Underneath sit a single Paste a link field and rows for From Library, Paste Text, and Google Drive, each of which opens its own page with a Back button. The project you are saving to is a row at the bottom, and Next appears once you have added something. See Scholarly on Mobile.

Desktop create windows show a Saving to chip in the header naming the project your sources and finished work will land in. It defaults to the project you used most recently, switch projects, choose No project, or create a new one inline without leaving the window. See Projects.

Supported File Types

Category	Formats
Documents	PDF, Word (.docx), PowerPoint (.pptx, .ppt)
Text and data	Plain text (.txt, .md), CSV/TSV, JSON, calendars (.ics), LaTeX, SVG
Code	Python, JavaScript/TypeScript, Java, C/C++, Rust, Go, and 30+ more
Images	JPEG, PNG, GIF, WebP, BMP, TIFF, HEIC, HEIF, AVIF
Audio	MP3, M4A, WAV, WebM, OGG
Video	MP4, MOV, WebM, M4V, AVI, MKV
URLs	Website URLs, YouTube video links

Each file can be up to 8 MB on Free, 300 MB on Premium, or 1 GB on Laureate.

The free plan includes 1 lifetime file upload (it does not reset); paid plans upload without limits. See Plans and Limits.

If your upload allowance is already used up, Upgrade is offered before you pick a file rather than after you've chosen one and waited. You can still bring in sources you already have, from your Library or Google Drive, without upgrading.

Scanned PDFs (image-only documents with no selectable text) are supported. Clear, legible scans produce the best results.

Text and data files (notes, CSVs, code, calendars, and more) are saved automatically as editable library files: each gets its own page where you can preview, edit, or chat with it, and reuse it as a source for any AI tool.

For a detailed breakdown of what each format can do, see the Supported File Formats guide.

What an Upload Looks Like

Every file and link you add appears in the Add content window as a pill: the same compact row chat uses, showing its type and size. Nothing covers the window while files upload, so you can keep adding sources or keep typing while they work:

• Each pill carries its own progress, and turns ready or red in place when it finishes.
• A file that fails keeps its reason on the pill, with Retry and Remove right there. You do not lose the rest of the batch to one bad file, and the explanation does not vanish like a toast.
• A file over your plan's size limit stays in the list with how far over it is, so you can see which one to swap out instead of guessing.
• The next step waits until every pill is ready, so a creation never starts on a half-uploaded source.

Deep Research works the same way, and there you can drop files straight onto the composer. Library items, Google Drive files, and pasted links all appear as pills next to your uploads.

After Uploading

When you upload a file, Scholarly processes it and shows you follow-up actions depending on the file type:

• Create Video Lecture: Generate a narrated video lecture.
• Create Podcast: Turn the content into an audio conversation.
• Ask AI: Open chat to ask questions about the content.
• Create AI Slides: Build a slide deck from the selected material.
• Create Flashcards: Generate a flashcard set from the material.

Video and Podcast lead the suggested actions. Open the rest of the grid or More for quizzes, flashcards, and other tools:

• Create Quiz: Build a quiz based on the content.
• Combine sources: Most creators accept 1 source on Free, 3 on Premium Lite where offered, 10 on Premium, or 20 on Laureate.

When you pick a podcast, video lecture, or slide deck, a short customisation panel appears before generation starts, pick a style preset, voices, length, focus areas, AI model, or add custom instructions. Your choices are kept even if you step back to change the source files. For the details of each option, see the Podcasts, AI Video Lectures, and AI Slides guides.

On a phone the customisation step is one screen with the core choices only: style, then language, voice, resolution and length, then instructions, then Create. Model, appearance, expert styles, and scheduling stay on desktop. If the creation would spend a free AI Creation Credit, Scholarly asks first, so a stray tap cannot use it up.

Generating from a long PDF? Every AI create window includes a page selector, so you can pick exactly which pages the AI works from before it generates.

Upload two or more related files at once and Scholarly offers to group them into a folder for you, one click keeps the batch together. See Folders and Organisation.

You do not have to choose an action right away. Uploaded content is saved to your library and you can come back to it later.

Your files keep their names

Uploaded documents and audio keep the filename you gave them, Scholarly does not rename your files during processing. Names with spaces and non-English characters are preserved. A processed copy may use a different extension when the document is converted, such as from Word to PDF. Recordings keep the name you saved them under, and you can still rename anything yourself by clicking its title.

If an upload is rejected

A file that can't be accepted tells you why rather than failing quietly, too large for your plan, an unsupported type, or empty. Oversized files are caught before the upload runs, so you find out immediately.

A Word, PowerPoint, or Excel file that is too complex to render stops on the first attempt and tells you to try a smaller file or upload a PDF instead, rather than leaving the upload spinning.

When a file is too large for your plan, the screen shows the file's size beside your plan's limit, names the plan that accepts it, and opens your plan options in one tap, on every upload and create screen.

Documents, text files, and images up to 50 MB are read as soon as you choose them, so a file that iCloud, Drive, or another app moves afterwards still uploads when you press Create. If a file truly can no longer be read, you get Choose file again rather than a Retry that could not work.

See Fixing Common Problems.

If a file can't be read at all

Some files upload fine and still have nothing in them to work with, a blank photo, a PDF or text file with no extractable text, audio that is only music or applause. Scholarly tells you that rather than generating something from nothing.

On the Free plan, your free upload is returned so you can add a better one, and the unreadable file moves to Deleted.

Scholarly also checks a source before a creation runs: pick one in a create window and you get a note if it turns out to be a sign-in page, mostly menus and repeated headers, unreadable text, or empty, with a suggestion for what to use instead. It is advice, not a block. The full guide is Getting Good Results From Your Sources.

PDFs

Uploaded PDFs get their own viewer page with:

• A full document viewer with page navigation.
• AI chat sidebar for asking questions about the content.
• Page-aware AI that knows which page you are reading.

When you generate slides, study guides, worksheets, video lectures, infographics, or mind maps from a PDF, the AI uses extracted text to locate relevant pages, then reads those pages visually when needed. This helps it account for diagrams, equations, tables, scans, and handwriting instead of relying only on extracted text.

The page picker reaches every page of the document. If your plan reads 32 pages per document, you can choose any 32 in a row, pages 90 to 121, say, not just the first 32. On a long document this is the single setting with the biggest effect on the result: create from chapter 9, not from "the textbook".

Audio Files

Audio uploads (MP3, M4A, WAV, WebM, OGG) create a recording page with:

• Automatic transcription with timestamps.
• AI-generated summary and topic list, written as soon as transcription finishes.
• A playback controls with speed adjustment.
• AI chat grounded in the transcript.

Video Files

Upload a video file (MP4, MOV, WebM, M4V, AVI, or MKV) directly and Scholarly gives it its own page with:

• Automatic transcription, with chapters generated from the content.
• An AI-generated summary.
• AI chat grounded in the transcript.
• One-click flashcard generation from the transcript.

YouTube Videos

Paste a YouTube URL and Scholarly extracts the video transcript. You can then generate flashcards from the transcript or discuss the video content with AI chat. If a video has no readable captions or transcript, upload the audio or video file directly instead.

Website URLs

Paste any website URL and Scholarly extracts the page content. Use it to generate flashcards or as context for AI chat.

Organisation

All uploaded content appears on your home page. From there you can:

• Move to folders: Drag items into folders or use the menu to organise.
• Rename: Click the title to rename any uploaded item.
• Pin: Pin frequently-used content to the sidebar for quick access.
• Delete: Delete content you no longer need. Deleted items move to Library → Filter → Recently deleted, where you can restore them at any time. See Deleting and Restoring Content.

Tips

• Upload multiple files at once by selecting several in the file picker or dragging a batch onto the page.
• After uploading a PDF, try "Give me the gist" in AI chat to get a quick overview before diving in.
• Use the upload modal from the flashcard creator to generate cards immediately from a new file.
• After a successful upload, the useful next step is making something from it or starting a chat, the file on its own is a source, not the result.

Related

• Supported File Formats, every format, and what each one can be turned into.
• Paste Text, adding material that does not live in a file.
• Connections, using Google Drive files as sources.
• Plans and Limits, file size, PDF pages, and how many sources you can combine.
• Getting Good Results From Your Sources, what reads well, what doesn't, and how to check in ten seconds.
• When a Creation Fails, what happens when a source stops a creation.
• Turning Work Documents into Training Material, what to do with a policy, SOP, or deck once it is in.