MarkItDown is a Microsoft Python utility and command-line tool that converts files and office documents into Markdown for use with large language models and text-analysis pipelines. It aims to preserve document structure such as headings, lists, tables, links, and other content rather than produce high-fidelity human-facing document conversions.
Its built-in converters handle formats including PDF, PowerPoint, Word, Excel, images, audio, HTML, CSV, JSON, XML, ZIP files, YouTube URLs, and EPUBs. It can be used through a Python API, command line, Docker, or third-party plugins; optional integrations support OCR with an LLM vision client, Azure Document Intelligence, and Azure Content Understanding, including multimodal conversion and YAML front-matter field extraction. The repository notes that conversion performs I/O with the current process's privileges, so untrusted inputs must be sanitized and the narrowest conversion method should be used.