markitdown vs pdf-craft
Document conversion tools compared
markitdown converts a range of file types into Markdown for text analysis and LLM workflows. pdf-craft focuses on using OCR to turn scanned PDFs into editable Markdown or EPUB, with optional translation workflows.
markitdown: Convert Documents and Files to Markdown
MarkItDown converts documents and other files into Markdown for LLM and text-analysis workflows. It offers a Python library and command-line interface, with optional format-specific dependencies and plugins.
pdf-craft: Convert Scanned PDFs into Markdown and EPUB
PDF Craft uses OCR to turn scanned books and documents into editable Markdown or EPUB, with optional translation and translated PDF output. It is a Python library for developers and readers who need to process scanned material.
| markitdown | pdf-craft | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 188k | 6.3k |
| Forks | 13.9k | 460 |
| Last analyzed | Oct 4, 2026 | Oct 3, 2026 |
Key differences
- markitdown handles many input types, including office files, HTML, images, audio, EPUB, ZIP, and YouTube URLs; pdf-craft centers on scanned PDFs.
- markitdown extracts readable text and basic structure, while pdf-craft uses OCR to process scanned pages and can organize results as an EPUB with metadata and a table of contents.
- markitdown offers a Python API and command-line interface; pdf-craft provides synchronous and asynchronous Python APIs.
- markitdown supports optional plugins and Azure extraction integrations; pdf-craft supports remote or local OCR backends and optional translation workflows.
- Both projects use Python and the MIT license. markitdown lists 188k stars and 13.9k forks, while pdf-craft lists 6.3k stars and 460 forks.
Choose markitdown if you…
- need to convert a mix of document and media formats into Markdown.
- want a command-line tool as well as a Python API for conversion.
- prioritize text and basic structure over faithful visual reproduction.
Choose pdf-craft if you…
- need OCR to convert scanned PDFs into editable Markdown or EPUB.
- want to create translated or bilingual EPUBs, or write translated text onto PDF pages.
- need synchronous and asynchronous Python APIs for scanned-document workflows.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.