GitHub tool · install with pip
Turn any file into clean Markdown.
markitdown is Microsoft's tool for converting messy files into clean Markdown that an LLM can actually read. Feed it a PDF, a Word doc, a PowerPoint, an Excel sheet, an image, or an audio file, and it gives you back structured text with headings, lists, links, and tables kept intact. It is the step that makes "here is a 40-page PDF, summarise it" actually work.
What it handles
documentsPDF, Word, PowerPoint, Excel into Markdown.imagesreads EXIF and runs OCR / captions.audiotranscribes speech to text.web + dataHTML, CSV, JSON, XML, and ZIP archives.
How to use it: run it on a file from the command line and pipe the Markdown into a file, or wire it up as an MCP server so Claude can convert files itself before reading them. Great for feeding documents into any of the other guides here.
Install (paste into your terminal)
🔒 Drop your email to reveal the install + repo
Get it, free.
Drop your email and the install command and repo link unlock instantly, plus every other guide and resource in the library. One email a week, unsubscribe anytime.