Framework
MarkItDown
MarkItDown is an open-source AI framework from Microsoft, launched in 2024, made for developers.
A Python tool that converts PDFs, Office files, images and more into Markdown for LLMs.
Main jobs: Document parsing. It is open source and free to use. You can use it in the terminal, offline on your own machine and on your own server.
Markdown version of https://godooo.ai/en/framework/markitdown. Every page on this site has one: add .md to its address.
At a glance
- Type
- Framework
- Made by
- Microsoft
- Launched
- 2024
- Galaxy
- Models & APIs
- Open source
- Yes · MIT
- Source code
- github.com/microsoft/markitdown
- GitHub stars
- 186,740
- How you run it
- Terminal · Runs offline · Self-host
- Made for
- Developers
- Website
- github.com
What it can do
Document parsingmain jobunconfirmed
“MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines.”— github.com, 2026-09-24
Speech to textsupportedunconfirmed
“Audio (EXIF metadata and speech transcription)”— github.com, 2026-09-24
Text recognition (OCR)supportedunconfirmed
“Images (EXIF metadata and OCR)”— github.com, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- DoclingOpen source, freeAlso does: Document parsing, Text recognition (OCR), Speech to text
- MinerUOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- PaddleOCROpen source, freeAlso does: Document parsing, Text recognition (OCR)
- MarkerOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- SuryaOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- UnstructuredOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- RAGFlowOpen source, freeAlso does: Document parsing
- PDF SkillAlso does: Document parsing
- LlamaIndexOpen source, freeAlso does: Document parsing, Text recognition (OCR)
- FirecrawlOpen source, freeAlso does: Document parsing
- FastGPTOpen source, freeAlso does: Document parsing; no code needed
- Firecrawl MCP ServerOpen source, freeAlso does: Document parsing
Questions
What is MarkItDown?
MarkItDown is an open-source AI framework from Microsoft, launched in 2024, made for developers. A Python tool that converts PDFs, Office files, images and more into Markdown for LLMs.
Is MarkItDown free?
Yes. MarkItDown is open source (MIT) and free to use.
Is MarkItDown open source?
Yes, under the MIT license. The source code is at https://github.com/microsoft/markitdown.
Can MarkItDown run locally?
Yes. MarkItDown can run offline on your own machine. It can also be self-hosted on your own server.
What can MarkItDown do?
Main jobs: Document parsing. It can also do: Speech to text, Text recognition (OCR).
Who makes MarkItDown?
MarkItDown is made by Microsoft.
What are open-source alternatives to MarkItDown?
Open-source ones: Docling, MinerU, PaddleOCR, Marker, Surya, Unstructured, RAGFlow and LlamaIndex. Others: PDF Skill.
Sources
- github.com/microsoft/markitdownchecked 2026-09-24