PDF to Markdown Converter
Turn a text PDF into clean Markdown for LLM prompts, notes or docs. Shows an estimated token count. Free, no signup, files never leave your browser.
Drop your PDF here
or click to choose a file — no size limit, no signup
🔒 Files never leave your browser — all processing happens locally.
How it works
- Drop a text-based PDF into the box above.
- The tool extracts the text, rebuilds headings and paragraphs, and estimates the token count.
- Download the .md file or paste it straight into ChatGPT or Claude.
Frequently asked questions
Why convert a PDF to Markdown for ChatGPT or Claude?
LLMs read Markdown far better than raw PDF text: headings survive, paragraphs stay intact, and you waste fewer tokens on layout junk. Markdown is also easy to split into chunks.
Does it work with scanned PDFs?
No. This tool supports text-based PDFs only. Scanned PDFs are images of text and would need OCR, which this tool intentionally does not include. The tool warns you if your file looks scanned.
How accurate is the token estimate?
It uses the common approximation of one token per four characters, which is typically within ±15% for English text — close enough for prompt budgeting.
How are headings detected?
The converter compares each line's font size against the document's body text size; larger or bold short lines become #, ## or ### headings.
Is my document uploaded?
No. Text extraction runs entirely in your browser — nothing is sent to any server.