Marker
Document extractionAn open-source tool that converts PDFs, ePub, and more into clean Markdown quickly and accurately.
Marker converts documents — PDFs, ePub, office files — into clean Markdown, JSON, or HTML. It handles tables, equations, code blocks, and reading order well, and is built to run fast on a GPU.
It is open-source, with an optional hosted API for teams that would rather not run the models themselves.
Where it's ideally used
A strong fit when you need fast, accurate document-to-Markdown conversion and can run it on your own GPU.
Where it doesn't fit
Best results lean on GPU access — less convenient for a purely CPU-bound or low-resource environment.