PDF · Markdown
Convert PDF to Markdown
Drop a PDF and get a clean Markdown file back: the text of every page in reading order, under a heading for each page, in a format AI tools, wikis and note apps read easily. Scanned pages are run through OCR automatically.
● Runs in your browser. Your files are never uploaded..pdf.jpg.png.docx.xlsx.xls.csv.txtWhat you get
quarterly-update.pdf · 6 pages, one of them scanned becomes:
# quarterly-update.pdf
## Page 1
Quarterly update
Revenue grew 12% on the last quarter, helped by two new distributors in Gujarat.
## Page 2 (OCR)
The board will review pricing in March.
Good for
- Reports, contracts, policies and manuals you want to paste into ChatGPT, Claude or Gemini
- Research papers and notes for Obsidian, Notion or a Git repository
- Mixed PDFs where some pages are typed and some are scanned
- Long PDFs: each page is processed in turn, so 100+ page files are fine on Pro
Worth knowing
- Multi-column layouts can come out with the columns interleaved. Check them after converting.
- Images and charts are skipped. Their captions and surrounding text are kept.
- Password-protected PDFs need to be unlocked first.
How it works
- Drop your file into the box above, or tap to choose it. Several files at once work too.
- The file is converted inside your browser. Scanned pages and images are read with OCR in the languages you pick.
- Preview the Markdown, copy it, or download it as a .md file.
Questions
Does it keep the layout?
It keeps the text and line breaks in reading order, with a Markdown heading for each page and a note on pages that were read with OCR. Fonts and positioning are dropped. Tables in PDFs come out as lines of text; for exact tables, convert the original Excel or Word file instead.
What happens with scanned pages?
Any page with little or no selectable text is treated as a scan and read with OCR in the languages you pick above. English is selected by default.
Why Markdown and not plain text?
Markdown keeps the structure of the document (headings, lists, emphasis) in a few characters, so AI tools understand it better and it uses fewer tokens than the original PDF.
Related guides
- PDF to Markdown for AI: why plain text beats uploading the PDF
- How to use fewer tokens when you give documents to ChatGPT or Claude
- How to give a very long document to an AI assistant