MarkItDown

MarkItDown brings Microsoft's open-source MarkItDown utility to the browser, turning almost any document into clean, structured Markdown optimized for LLMs, RAG pipelines and documentation workflows. Upload PDF, DOCX, PPTX, XLS/XLSX, HTML, TXT, CSV/TSV, JSON, XML, EPUB or Jupyter notebooks, paste a table, enter a public URL, or drop in PNG/JPG/WebP images for OCR. Headings, lists, links and tables are preserved where the source allows, while AI OCR handles scanned PDFs, recovers tables and converts math to LaTeX. Privacy-conscious users can process files locally in the browser, or pick fast server conversion for heavier jobs. Extra tools include Markdown to PDF/Word, a Markdown viewer, and a cheatsheet. The free tier needs no account (3 files per batch, 20MB files, 10 OCR pages a month); Pro raises limits to 100MB files, 30-file batches, more OCR and unlimited saved results. Available in six languages.