Convert PDF to Markdown
Get a PDF back as plain, portable Markdown. Headings become #, lists become lists, and detected tables come out as GFM pipe tables — ready to paste into a README, a wiki, or an AI prompt.
Get a PDF back as plain, portable Markdown. Headings become #, lists become lists, and detected tables come out as GFM pipe tables — ready to paste into a README, a wiki, or an AI prompt.
Drop in the PDF you want as Markdown.
Keep images (delivered as a .zip alongside the .md) or drop them for a single plain file. Turn on AI cleanup for messy or scanned-looking documents.
Open it in any editor — the structure is real Markdown, not a wall of text.
Headings are ranked by size, lists keep their markers, and tables come out as proper Markdown tables.
Markdown is the format LLMs and git both read best — far more useful than a PDF or a .docx.
By default they're extracted into an images/ folder and delivered as a .zip with the Markdown, which links to them. Turn images off to get a single plain .md instead.
Yes — detected tables are reconstructed as GitHub-flavoured pipe tables, using the same table detection that powers PDF → Excel.
It re-reads the extracted structure to merge paragraphs broken across lines, fix reading order, and reclassify headings and lists. Useful on messy documents; unnecessary on clean ones.
A scanned page has no text layer, so run OCR first to get selectable text, then convert.
Your upload and the Markdown output are deleted from storage within an hour.