MarkItDown

Open Source📊 data

A lightweight Python tool for converting files and office documents to Markdown for use with LLMs and text analysis pipelines.

github.com →

📊Categorydata

🆓PricingOpen Source

About

MarkItDown is an open-source Python utility from Microsoft that converts a wide range of file types into Markdown while preserving document structure such as headings, lists, tables, and links. It supports PDF, Word, PowerPoint, Excel, images (OCR and EXIF), audio (transcription), HTML, CSV/JSON/XML, ZIP archives, EPubs, and YouTube URLs. Designed to feed LLMs and text analysis tools, it is most useful for developers building data and AI pipelines. It is distributed under the MIT license and installable via pip.