BabelDOC
LLM-based open-source PDF translator — preserves layout, bilingual side-by-side
An LLM-based open-source PDF translation tool that preserves layout with bilingual side-by-side output. Note: AGPL-3.0 — mind the license for commercial use.
Translate documents, parse PDFs, and extract text with OCR.
Key features
- PDF scientific paper translation and bilingual comparison library
- Command line interface and Python API
- Focuses on English-to-Chinese translation with basic English target support
- Designed to embed into other programs or use standalone
Good for
- Researchers reading foreign-language papers in bilingual layout
- Developers embedding PDF translation into their own tools
Stack & tags
Pythonpdf-translationbilingualscientific-papersclipython-librarychinese
Quick start
uv tool install --python 3.12 BabelDOC
babeldoc --helpFrom the project README on GitHub.
Similar open-source projects
微软 MarkItDown
★ 187,737Microsoft's open-source Python tool — convert PDF/Word/PPT/audio/YouTube to clean Markdown
DeepSeek-OCR
★ 23,926DeepSeek's novel OCR document model — "contextual optical compression"