How do I convert a PDF to Markdown?

Drop your PDF above: the text layer is extracted in your browser, headings are inferred from font size, bullet characters become markdown list items, and page breaks can be kept as --- separators. Copy the result or download it as a .md file.

Does it work on scanned PDFs?

No — scanned PDFs are images without a text layer. Run the document through an OCR tool first, then convert the result. Text-layer PDFs (exported from Word, Google Docs, LaTeX) convert cleanly.

How are headings detected?

The median font size of the document is computed, and lines set significantly larger are promoted: roughly 70%+ larger becomes a top-level heading, 40%+ a second level, 15%+ (if short) a third level. Verify important documents — decorative fonts can confuse size-based inference.

Is this good for RAG and LLM ingestion?

Yes — that is the design target. Clean markdown with heading structure and page-break markers chunks well for embeddings. Table-heavy layouts flatten to text, so verify financial documents.

PDF to Markdown

Extract a PDF's text as clean Markdown — headings detected from font size, bullets converted, page breaks preserved. Perfect for LLM/RAG ingestion, notes, and docs. Runs entirely in your browser.

Drop a PDF here

or click to browse — text-layer PDFs (scans need OCR)

Headings

Insert --- between pages

Why markdown, and honest limits

• Headings are inferred from relative font size (≥70% larger = h1, ≥40% = h2) — check important docs
• Bullet glyphs (•, ▪, -, ·) become markdown list items
• Tables come out as text — complex layouts flatten; this extracts the text layer, not the layout
• Scanned PDFs have no text layer — use OCR first, then convert
• Related: PDF to Text · HTML to Markdown