microsoft/markitdown

MarkItDown is a lightweight Python utility from Microsoft that converts PDFs, Office documents, images, audio, HTML, and other formats into Markdown optimized for LLM and text-analysis pipelines. It preserves document structure such as headings, lists, tables, and links while offering both a CLI and Python API. Optional integrations add OCR, speech transcription, Azure Document Intelligence, Azure Content Understanding, and third-party plugins.

Key Highlights

• Broad format support for PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV/JSON/XML, ZIP, EPUB, and YouTube URLs.
• LLM-ready Markdown that preserves headings, lists, tables, and links for RAG and text analysis.
• Flexible usage via the markitdown CLI, stdin piping, Docker, or the Python MarkItDown API.
• Extensible integrations including Azure Document Intelligence, Azure Content Understanding, LLM image descriptions, and plugins such as OCR.
• Modular optional dependencies let you install only the converters you need.

Best For

Developers, data engineers, and AI teams building RAG, document ingestion, or text-analysis pipelines who need fast, structure-preserving conversion without heavy infrastructure.