PDF to Markdown converter

How it works

1. 1

   Drop your PDFs

   One file or up to twenty at once, each up to 50MB: reports, manuals, papers, policies.

2. 2

   Your browser rebuilds the structure

   PDF.js reads the text layer on your device. Font sizes become headings, bullets become lists, and line breaks inside a paragraph are joined back up.

3. 3

   Copy or download the .md

   Preview the Markdown, copy it to your clipboard, or save a .md file for each PDF. Nothing is uploaded or stored.

What the converter cleans up

Copying text out of a PDF usually gives you a hard line break at the end of every printed line, words split by hyphens, and the same header, footer and page number repeated on every page. This converter rebuilds each paragraph from the line spacing, re-joins words a line break split at a hyphen, and removes lines that repeat at the top or bottom of most pages, along with bare page numbers.

What's left is ordinary Markdown: # headings, - and 1. lists, and blank lines between paragraphs. It opens in any text editor, Obsidian, Notion, GitHub or a docs site, and pastes cleanly into a chat.

Where PDF to Markdown falls short

A PDF is built for printing, not for structure, so every converter has to guess. Bold text used as a heading at body size stays a paragraph. Tables, footnotes and side-by-side columns don't map neatly to Markdown and come out as plain lines. Images and charts are left out. For a typical report or manual the result needs a quick skim; for a table-heavy document, expect to fix the tables by hand.

Related free tools

To check length before converting, the PDF word counter gives words, pages and tokens per file. The token counter tells you whether the Markdown fits a model's context window. If you'd rather have one PDF split into clean, chunked text for an AI tool, try the free knowledge base builder.

Frequently asked questions

How do I convert a PDF to Markdown?

Drop the PDF on this page. In a few seconds you get a Markdown preview you can copy, plus a Download .md button. There is nothing to install and no account, and the conversion happens in your browser tab rather than on a server.

How are headings and lists detected?

A PDF has no real headings, only text drawn in different sizes. The converter finds the size most of the body text uses, then treats short lines set noticeably larger as headings: the largest size becomes #, the next ##, and anything smaller ###. Lines that start with a bullet or a dash become - items, and lines that start with 1. or 1) become a numbered list.

What happens to tables, images and columns?

Images are skipped, since Markdown output is text only. Tables come out as plain lines in reading order, not Markdown tables, because a PDF stores cells as loose pieces of text with no grid; check any table you need and rebuild it by hand. Two-column layouts are read line by line across the page, so for those, check the result before you rely on it.

Is my PDF uploaded anywhere?

No. The file is opened and converted inside your browser and the .md file is created on your device. It is never sent to our servers or anyone else's, which makes it fine for contracts, internal docs and other private files.

Why convert a PDF to Markdown for ChatGPT or Claude?

Markdown keeps the structure that matters to an AI model, such as headings and lists, while dropping the page furniture that gets in the way: repeated headers, footers and page numbers. The result is usually smaller and easier for the model to search and quote than the raw PDF. Check its size with the token counter before you paste it in.

It says my PDF looks scanned. What can I do?

A scanned PDF is a set of page photos with no text layer, so there is no text to convert. Run it through OCR (text recognition) first, for example Adobe Acrobat's Scan & OCR tool, or open it with Google Docs from Google Drive, then convert the new copy here.

More free tools

All free tools →

Related guides