PDFtoMD

PDFtoMD is a straightforward web tool that turns PDF files into Markdown — no sign-up required for the first few conversions. You drop a PDF in, and it spits out a .md file with headings, lists, and paragraphs properly formatted. Scanned documents and image-based PDFs are handled too, thanks to built-in AI-powered OCR that reads the text and reconstructs tables, formulas, and even seals as structured Markdown. The free tier gives you 10 pages per day, which is plenty for light use.

How does it work? For digital PDFs (like exports from Word or Google Docs), the tool reads the text layer directly, so you get high-fidelity output without OCR noise. For scans, free accounts get fast line-level OCR, while paid plans unlock a Vision mode that uses a state-of-the-art vision model to preserve complex layouts. Conversion happens in seconds for most documents. Your output is saved to your account history, so you can re-copy or re-download it later. There's nothing to install — it's all in the browser.

Who should use this? Anyone who regularly needs to extract text from PDFs for editing, note-taking, or publishing. It's great for writers moving between Obsidian or Notion, developers who want to version-control documentation, and researchers preprocessing PDFs for AI workflows (RAG pipelines, summarizers, etc.). If you only need a few pages a day, the free plan is all you need. For heavier use, the paid plans (starting at $15.90/month) bump up the page and file size limits.