microsoft/markitdown

Health v2 · maintenance only

Adoption not part of the score

176487 stars · 12952 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

MarkItDown is a lightweight Python utility from Microsoft that converts many file formats (PDF, Office documents, images, audio, HTML, EPub, and more) into Markdown. It is designed to feed documents to LLMs and text analysis pipelines while preserving structure like headings, lists, tables, and links.

Use cases

• convert pdf to markdown
• convert word documents to markdown for llm
• extract text from powerpoint and excel files
• prepare documents for rag pipelines
• ocr images to markdown text
• transcribe audio files to text
• convert html pages to markdown

When to choose

• you need to feed documents into LLM or text-analysis pipelines
• you want token-efficient Markdown output preserving document structure
• you need a single tool handling many formats (Office, PDF, images, audio, EPub)
• you want a simple pip-installable Python library or CLI

When to avoid

• you need high-fidelity document conversion for human consumption
• you require pixel-perfect layout or formatting preservation
• you need to process untrusted inputs without sanitization, given its I/O runs with process privileges

Facets

cli-tool · maturity active

pdf ocr speech-recognition parser llm-inference developer-tools large-language-models pdf files python cli cross-platform markdown-conversion document-parsing file-conversion office-documents llm-preprocessing natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/markitdown")