Supported file types and size limits

Ritsu accepts most common study materials. Here's the full list, what gets extracted, and the per-file limits.

Supported types

Type	How to add it	What Ritsu reads
PDF	Upload .pdf	Text, with OCR for scanned pages
Word	Upload .docx	Text
PowerPoint	Upload .pptx	Slide text
Markdown / plain text	Upload .md, .txt	Text as written
Images	Upload .png, .jpg, .jpeg, .webp	Text read from the image
Jupyter notebook	Upload .ipynb	The notebook's cells
YouTube	Paste a video link	The video's captions, including auto-generated ones
Web page	Paste a link	The page's main text
Pasted text	Paste into the text box	Text as written

Size + length limits

Limit	Free	Plus	Pro	Ultra
Pages per source	40	100	200	500
YouTube video length	30 min	2 hours	6 hours	12 hours
Sessions per learning project	5	20	Unlimited	Unlimited
File size	20 MB	20 MB	20 MB	20 MB
Total storage	10 GB	10 GB	10 GB	10 GB

There's no daily upload limit; if you upload many files in a row, you may be asked to wait a minute. Processing a source uses credits — reading a PDF costs around 1 credit per page. The current limits for each plan are always on the pricing page.

What we DON'T support yet

• Live streams (use the recording after the stream ends)
• Encrypted / DRM-protected files (Audible audiobooks, ePubs from Apple Books, etc.)
• Protected video platforms (Coursera, Udemy DRM streams) — paste the transcript text directly instead
• Spreadsheet-style content (.xlsx, .csv) — paste as text or convert to PDF first
• Audio and video files (.mp3, .mp4 and similar) — for a lecture on YouTube, paste its link instead
• E-books (.epub) — convert to PDF first

File quality matters

A clean, well-structured source produces better PoKs than a messy one. Specifically:

• Searchable PDFs beat scanned PDFs (no OCR errors)
• Original transcripts beat auto-captions (creator-uploaded subtitles are usually 95%+ accurate)
• Single-language sources beat mixed-language (Ritsu handles mixed but auto-detection sometimes flips mid-source)
• Headings + chapter structure in the source produces sharper PoK extraction

Tips

• Convert obscure formats to PDF first (most apps export to PDF) — that's our most-tested path.
• For lecture videos, caption quality matters more than anything else. Creator-uploaded subtitles beat auto-captions.
• For long sources, upload a chapter or two at a time. It keeps you inside your plan's pages-per-source limit and gives sharper PoKs.

Trouble

• "Unsupported format" — verify your file extension matches the table. Some platforms add hidden extensions (.pdf.gz, .docx.zip).
• Upload starts then fails — usually a size issue. See Upload failed.