Convert PDFs, Word files and slides into plain Markdown
Made by Microsoft
View profile on GitHub (opens in a new tab)A small Python tool that turns PDFs, Word documents, spreadsheets, slides, images, audio and more into Markdown, keeping headings, lists, tables and links.
It is meant to get files into a form AI tools can read.
Can I use this?
You'll need Python and a terminal · Setup needed
Worth knowing The project says the output is meant for text analysis tools rather than for people, so it is not a high-fidelity document converter. It also warns that it reads whatever the running program can reach, so untrusted files should be handled carefully. BuildTube has not run or verified this software.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 20 September 2026. It stays on BuildTube so you can still find it.
- 188,833 people have starred it on GitHub.
Numbers checked on 6 October 2026; not refreshed since.
Behind it
See the code on GitHubBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?