PDF to Markdown / Text — for pasting into ChatGPT or Claude
Upload a PDF and get clean Markdown text back, ready to paste as context into an LLM prompt. Runs entirely in your browser when possible — the file never has to leave your device.
When this helps
People prepping LLM context
Copy-pasting text out of a PDF reader loses formatting and page structure.
Upload the PDF here and paste the resulting Markdown straight into your prompt.
Researchers / analysts
Need the text of a report quickly, without keeping a full PDF viewer open.
Extract once, then search/skim the plain text instead.
Developers
Want to script something around a PDF's contents without pulling in a heavy PDF library.
Use this to sanity-check what a PDF's text layer actually contains before writing extraction code.
FAQ
- Is my file uploaded to your servers?
- No — if your browser supports WebAssembly (WASM, a technology that runs software safely and quickly right inside your browser), the file never leaves your device. If that isn't available, it falls back to normal server-side processing, which also discards the file immediately after returning the result — nothing is stored either way.
- Does this work on scanned PDFs (no text layer)?
- Not yet — this extracts the text layer that's already in the PDF. A scanned PDF with no embedded text needs OCR, which isn't included here.
- What's the token estimate based on?
- A rough character-count heuristic, not a real tokenizer — treat it as a ballpark for whether the result fits your model's context window, not an exact count.
- What's the file size limit?
- 20MB per file on the free tier.