Turn your PDF into a video you can learn from

Yes, to start. The Free plan includes one lifetime AI Creation Credit, shared across every Scholarly tool, and it can make one narrated PDF video of about 2 minutes at 720p with Scholarly branding, with no credit card. Free uploads are up to 8 MB and PDFs are read up to 32 pages, so pick a page range for a longer file. Watching and sharing by link are free; MP4 download, 1080p, a custom length up to 45 minutes, and 15 AI Creation Credits a week come with Premium.

It explains them. Scholarly writes a teaching script from the pages you pick and narrates it over new scenes, using figures from your PDF where they help. It does not export each page as a timed frame, so if you need the PDF shown exactly as it is, a plain page-to-video converter is the better tool.

Upload the PDF on this page, choose the pages, a style and a voice, and wait while the AI generates a narrated, animated video lecture (a short one is usually ready in about 3 to 12 minutes). Then watch it with chapter navigation, a searchable transcript, and AI chat. You can convert a single lecture slide deck or textbook chapter, or combine up to 10 PDFs (20 on Laureate) into one video on a paid plan. No script writing, slide design, or voice recording on your end.

Upload the PDF, choose the pages, a style and a voice, and Scholarly builds a narrated video from it. On a paid plan you then download the finished video as an MP4 at up to 1080p. On the Free plan you watch it in Scholarly and share a link, and there is no file download.

Yes, on any paid plan. Premium and Laureate download the finished lecture as an MP4, and turning the Scholarly logo off when you generate gives a watermark-free file; the export pack adds the companion slides PDF (Standard mode), the script, and caption files. On the Free plan you watch the video in Scholarly and share it with a view link that opens in the browser, but download is not included.

Not on Scholarly's Free plan. The free video is about 2 minutes at 720p, always shows the Scholarly logo, and cannot be downloaded. On a paid plan you can turn the logo off before you generate, which gives a watermark-free MP4.

It is a narrated lecture built from new scenes, not a recording of your PDF pages: a natural voice explains the material while diagrams, charts, equations, and step-by-step builds animate in sync, and the AI can add generated pictures or figures cut from your PDF pages. The video is 16:9 (Short video is vertical), split into chapters, with captions you can switch on, a searchable transcript, optional question checkpoints, and AI chat. Standard Fast is the default style; Standard, Illustrated, Math Lecture, Doodles, and Freestyle are the others, and Short video turns any of them into a vertical clip.

Yes. Every video Scholarly generates is narrated from start to finish. The AI writes the script from your PDF, then reads it aloud in the voice you pick when you create the video, synced to the visuals and chapters. Captions and a full searchable transcript come with it, so the same video also works with the sound off.

A short video is usually ready in about 3 to 12 minutes, and longer lectures take longer: a 45-minute lecture can take an hour or more. It runs on Scholarly's servers, so you can close the tab, and by default you get an email when the video is finished.

On the Free plan, a video lecture is a fixed length of about 2 minutes. On Premium and Laureate you set a target length up to 45 minutes before generating (15 minutes is the default), and the lecture is planned to that length, so a long PDF gets more chapters rather than a rushed pace. Each video costs 1 AI Creation Credit with the default model, plus 1 extra credit above 15 minutes and 2 extra above 30 minutes. The vertical Short format keeps its own fixed length.

The Free plan takes one PDF up to 8 MB and reads up to 32 pages per video: the first 32, or a range you choose. Premium takes files up to 300 MB and reads up to 1,000 pages per PDF, and Laureate takes files up to 1 GB and reads up to 3,000 pages. A 100 or 200 page PDF therefore needs a page range on Free or a paid plan, and it usually makes a clearer video when you cover one chapter or section at a time.

Yes. Before you create the video you can enter a page range or choose which sections of the PDF to cover, and add instructions such as which chapter to focus on. The narration is then written from the pages you selected. On the Free plan a video reads up to 32 pages.

Text-based PDFs like lecture slides, textbook chapters, research papers, and study guides work best. Scanned documents and image-heavy PDFs also work, though text-based files produce the most accurate results.

Yes. Scanned PDFs are read from the page images, so a clean, legible scan works. Blurry or low-contrast pages are the ones most likely to be misread, so check the transcript of the finished video. Handwritten pages can be uploaded the same way, as a scan or a photo.

Scholarly can cut figures from your PDF pages and show them in the video where they help. It can also redraw ideas as new diagrams, charts, tables and typeset equations, and explain them in the narration. It does not reproduce every page element one for one, because the video is a new explanation of the PDF and not a copy of it.

The script is written from the pages you select, so the video follows your document's terms and scope. AI can still misread a page or simplify a point too far, so read the transcript against the PDF before you rely on the video for an exam or share it with a team.

Yes. Turn on Use my script as written and the narrator reads your source word for word instead of writing a new teaching script. On paid plans the video runs to the script's own length, up to 45 minutes, and a longer script continues as Part 2. On the Free plan a longer script is cut to about 2 minutes.

There is no timeline or scene editor. While the video is being made you can send requests in the Ask for a change thread, and afterwards you can make a new version in another style, voice or language, or a longer remake on a paid plan. A new voice or a new language version uses 1 AI Creation Credit on the Auto model.

Yes, on a paid plan. Premium combines up to 10 PDFs in one video and Laureate up to 20; the Free plan takes one PDF per video. The AI combines the content into a single cohesive video lecture, which is useful for merging lecture slides with the corresponding textbook chapter.

Yes, lecture slide PDFs are among the strongest inputs. The AI reads the slides in order, narrates the bullet points in full sentences, and adds animated supporting visuals, reusing figures from the slides where they help. A short video from an instructor-provided deck is usually ready in about 3 to 12 minutes.

Yes. Upload the paper as a PDF, choose the sections you want explained, and Scholarly makes a narrated video with chapters, captions and a transcript. Figures can be cut from the paper's pages and shown in the video. The Free plan reads up to 32 pages per video, and paid plans read up to 1,000 or 3,000 pages per PDF.

Narration, captions, and the transcript can be generated in 70+ output languages and regional variants, including English, Spanish, French, German, Portuguese, Hindi, Arabic, Japanese, and Chinese. The PDF and the video do not have to share a language, so an English paper can become a Spanish or Arabic lecture. Arabic and Hebrew lectures are laid out right to left, and on-screen text follows the lecture's language.

Yes. Scholarly runs in the browser on a phone or a laptop, so there is nothing to install. Upload the PDF, start the video, and come back when it is ready: it is made on Scholarly's servers, and by default you get an email when it is finished.

Yes. After your video is generated, you can create flashcards from the content with one click and study them with spaced repetition. Exporting to Anki or PDF, downloading, and printing require a paid plan.

Yes. Every generated video includes a full, searchable transcript with timestamps. You can search for specific terms, click on any section to jump to that point in the video, or copy text for your own notes.

Yes. Share your generated video lecture with classmates or a study group by link, directly from Scholarly. Anyone who opens the link signs in with a free Scholarly account to watch it, with chapters, captions, and the transcript.

Scholarly reads the PDF as a teaching source and keeps definitions, equations, and figure references intact. The video includes chapters, transcript search, contextual AI chat, and flashcards. It suits learners, educators, researchers, and trainers.

Yes. If your notes are typed, paste them into Scholarly's text to video tool or upload the file directly; if they're handwritten, photograph or scan them to PDF and upload that. Scholarly also has a dedicated notes to video workflow that builds the same narrated, chaptered lecture from class notes - useful when your notes are messier than a polished document.

Yes. Paste a YouTube link and Scholarly imports the video as a study source the same way it handles a PDF - and can re-teach it as a condensed, chaptered video lecture with a transcript, AI chat, quizzes, and flashcards. It's the fastest way to compress a 90-minute recorded lecture into a focused review video.

When you need speed over depth. For a quick pre-exam skim, a summary or study guide is faster than watching. For finding one definition, AI chat or transcript search wins. For problem-heavy courses, practice questions build more skill than watching explanations. Video is strongest on your first pass through dense, unfamiliar, or visual material.

Yes. Upload a standard operating procedure, onboarding guide, process doc, or policy PDF, up to 10 files in one video (20 on Laureate), and Scholarly writes a teaching script only from that material, then generates a narrated video with chapters, captions, and a full transcript. Because the script comes from your document rather than the open internet, it uses your steps and your terminology. Review it before rolling it out, as with anything AI-generated. Compliance manuals and policy handbooks work the same way. Paid plans render up to 45 minutes at 1080p; Free renders one 2-minute video.

Yes. Text-based files produce the best results, and PDFs, Word documents, and slide decks all work. You can combine up to 10 files into one video (20 on Laureate) - for example an SOP plus the policy behind it - and when the document changes you update it and generate a fresh video in minutes instead of re-recording. The uploaded material stays in your workspace, so teammates can also chat with it and get cited answers.

Yes. Every video can be shared with a link and watched in the browser with chapters, captions, and a transcript, and paid plans can download a watermark-free MP4 to host in your wiki or anywhere else. Scholarly for Teams adds shared source libraries so everyone builds from the same approved material, invitations by email or link with Member and Admin roles, per-member activity, and one central bill for the seats you choose on Premium for Teams or Laureate for Teams; the team plan unlocks its formats and AI limits for every seat.