Turn a PDF into clean, AI-ready Markdown

Strip the clutter that wastes tokens and confuses AI models, and keep the structure that helps.

Processed on your device

or drop a PDF anywhere on this page. Files stay on this device.

How to turn a PDF into clean, AI-ready Markdown

To make a PDF AI-ready, open it here and press Make AI-ready Markdown. Puffin PDF reads the text in your browser, removes headers, footers and page numbers that repeat on every page, joins lines broken mid-sentence, and turns larger text into Markdown headings. You get a .md file, and a token estimate, to paste or upload into ChatGPT, Claude, Gemini or a RAG pipeline.

  1. Select a PDF, or drop it on this page.
  2. Choose whether to mark where each page starts.
  3. Press Make AI-ready Markdown.
  4. Copy the text or download the .md file.

Questions and answers

Why not just upload the PDF to the AI?

Many AI tools read a PDF's text with its running headers, footers and page numbers mixed in, which wastes tokens and can split sentences. Clean Markdown is smaller and easier for a model to follow, and you choose exactly what it sees.

What are page markers for?

They add a short comment where each page starts, so you can ask the AI to cite page numbers in its answer.

Does it work on scanned PDFs?

A scan is a picture of a page, so it has no text to convert. Run OCR PDF on it first (also free and on your device), then convert the file OCR gives you.

Are my files uploaded?

No. The work is done by code running in your browser, so your file never leaves your device. You can check this yourself: open your browser's developer tools, switch to the Network tab and run the tool. No request carries your file.

Is it free? Are there limits?

Yes, it is free with no sign-up, no watermark and no daily limit. Because your own device does the work, it costs us almost nothing to run, so there is nothing to meter.

Other tools