Search iThub

Search tools, categories and collections. Type at least two characters.

Explore all tools
↑ ↓ to explore resultsEnter to open · Esc to close
M

MarkItDown

Microsoft's Python utility that converts files to Markdown for LLMs

Visit website Save

MarkItDown is a Python utility and CLI that converts PDF, Office, HTML, image and audio files to Markdown for LLM and text analysis pipelines.

Pricing
Open source
Deployment
Self-hosted
194,196stars14,608forks
1views
Updated

What is MarkItDown?

MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. The repository is published under the microsoft organization on GitHub. The README compares it to textract, with a focus on preserving document structure such as headings, lists, tables and links.

The output is meant to be consumed by text analysis tools, so it may not be the best option for high-fidelity document conversions for human reading. Supported inputs listed by the project include PDF, PowerPoint, Word, Excel, images with EXIF metadata and OCR, audio with speech transcription, HTML, CSV, JSON and XML, ZIP files, YouTube URLs and EPubs.

It requires Python 3.10 through 3.14 and installs with pip. Format support is split into optional dependency groups, so a team can install only the PDF, DOCX and PPTX extras instead of everything. Third-party plugins exist but are disabled by default. Azure Document Intelligence and Azure Content Understanding are optional cloud converters billed as Azure API calls, while the built-in converters use local compute only.

Key capabilities

  • Markdown output Converts PDF, Word, PowerPoint, Excel, HTML, images, audio, ZIP files and EPubs to Markdown.
  • Command line and Python API Run markitdown file.pdf or call the library, including piped input.
  • Selective installs Pick extras such as pdf, docx and pptx instead of installing every dependency.
  • Plugins Third-party plugins are supported and stay off until enabled.
  • Cloud options Azure Document Intelligence and Azure Content Understanding for higher-quality extraction, billed by Azure.
Advertisements

Where MarkItDown fits

  • Preparing documents for LLM and RAG input
  • Text analysis pipelines that need structure kept as Markdown
  • Batch conversion from scripts using the CLI
  • OCR of embedded images through the markitdown-ocr plugin and a vision-capable LLM
  • Audio and video handling through Azure Content Understanding

Install

pip install 'markitdown[all]'

Reviews of MarkItDown

No reviews yet

Be the first to share your experience with MarkItDown.

Loading review form…