#2727th of 33 in Data and scraping for AIFor data and documents, documents and ocr, science, health and research, research and papers
babeldoc
PDF paper translator that keeps layout and outputs bilingual PDFs
- Stars
- 9.8k
- License
- AGPL-3.0
- Last commit
- Aug 2026
- Last release
- Jul 2026
- Language
- Python
7,913 on 4 Apr 20269,797 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
BabelDOC translates scientific PDFs through an OpenAI-compatible LLM endpoint and rebuilds the layout, producing monolingual and bilingual PDFs. It ships a CLI and a Python API and is mainly meant to be embedded in other programs. It supports glossary CSVs with automatic term extraction, page selection, split translation for large files, and an OCR workaround for scanned documents.
Who it is for: Developers embedding layout-preserving PDF translation into their own tools
Strengths
- Outputs monolingual and bilingual PDFs, side by side or on alternating pages
- Glossary CSV support plus automatic term extraction for consistent terminology
- Works with any OpenAI-compatible endpoint, including local servers such as Ollama
- Offline asset package for air-gapped installs; TOML config file
Weaknesses
- Only OpenAI-compatible LLMs supported; not optimized for Bing or Google engines
- Mainly tested on English-to-Chinese; other language pairs untested
- README says the CLI is for debugging and gets no end-user support
- No built-in web UI; self-hosted WebUI is in PDFMathTranslate-next
What it needs
- Needs OpenAI-compatible LLM API, uv, Python 3.12
- Models: OpenAI-compatible APIs, gpt-4o-mini (default), glm-4-flash, deepseek-chat, Ollama
Quick answers
Is babeldoc open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Also in Data and scraping for AI
See all 33| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 94 out of 100 |
| 2 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 87 out of 100 |
| #4 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 86 out of 100 |
| #5 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 85 out of 100 |