Last updated: 11/12/2026Last verified: 2026-11-09
What is BabelDOC?
BabelDOC is an AGPL-3.0 library for translating scientific-paper PDFs into bilingual documents while preserving the original layout. It supports mixed formulas and text, offers both a command-line interface and Python API, and has an online beta available through Immersive Translate.
Key Features
- Bilingual PDF output designed to preserve the source document layout
- Support for PDFs containing mixed formulas and text
- Command-line interface for scripted or repeatable workflows
- Python package compatible with Python 3.10 through less than 3.14
- Documentation that describes installation with uv on Python 3.12
- Support for OpenAI-compatible models
- CSV glossary support for terminology control
- Automatic term extraction
- Online beta access through Immersive Translate
- AGPL-3.0 open-source licensing
- Python API for programmatic integration
Best For
Pricing
The BabelDOC library is free, open-source software under AGPL-3.0; you supply your own OpenAI-compatible model and API key. For end users, the README points to the online beta inside Immersive Translate and states it includes 1,000 free pages per month, with details in the FAQ on that page. Allowances shown inside the Immersive Translate app may differ from the README, so check the BabelDOC page for current limits before relying on them.
Pros & Cons
Pros
- Targets scientific-paper PDF translation rather than general text alone
- Preserves the source layout in bilingual output
- Handles documents containing both formulas and text
- Provides CLI, Python API, and library access
- Supports OpenAI-compatible models
- Includes CSV glossaries and automatic term extraction
- Uses an open-source AGPL-3.0 license
Cons
- The README says the CLI is mainly for debugging and that end users get no technical support for it.
- The README says the project mainly focuses on English-to-Chinese translation and other scenarios have not been tested yet.
- README known issues: author and reference sections can be merged into one paragraph, lines and drop caps are not supported, and large pages are skipped.
- The online experience is a beta, so availability or behavior may change.
- Configuring models, glossaries, or programmatic workflows takes some technical knowledge.
Alternatives
It is a closely related option for translating technical PDFs, and BabelDOC's information points to it for self-hosting.
DeepL offers AI translation for supported documents, making it a general alternative for users who prioritize a hosted translation workflow.
Google Translate provides document translation for supported file types and can serve users seeking a widely available online translation service.
Immersive Translate hosts BabelDOC's online beta and also provides broader translation features for web and document-reading workflows.
FAQ
Details
Platform
Features
- Bilingual PDF output that keeps the source layout, including mixed formulas and text
- CLI and Python package (Python >=3.10 and <3.14; the docs install it with uv on Python 3.12)
- OpenAI-compatible models, CSV glossaries, and automatic term extraction
- Online beta inside Immersive Translate, with self-hosting pointed at PDFMathTranslate-next
Languages
Known limitations
- The README says the CLI is mainly for debugging and that end users get no technical support for it. It also says BabelDOC Python APIs are internal and unsupported; the recommended call is pdf2zh_next high_level.do_translate_async_stream. The library documents only OpenAI-compatible models
- README known issues: author and reference sections merge into one paragraph, lines are not supported, drop caps are not supported, and large pages are skipped. The online beta says it cannot handle scanned or image-only PDFs; the OCR workaround is only for black text on a white background
- The in-app FAQ bills the beta in tokens: every user gets 500,000 tokens a month on GLM 4 Flash 250414, subject to upstream supply and server load. Named stronger models are Pro/Max only and draw on the member quota, up to 20 million tokens a month on Pro and 50 million on Max. A task pre-deducts 3,000 tokens per page, or 6,000 when automatic term extraction is on. Free uploads are capped at 166 pages per translation and Pro at 5,000 pages per file; the same UI says Pro unlocks 10,000 pages a month. The README still says the beta includes 1,000 free pages a month, so those published allowances do not match
- The README says the project mainly targets English-to-Chinese and that other scenarios have not been tested. The supported-languages page lists many more languages, says non-ligature languages have good support, and says languages that fully depend on ligatures are not supported. Online translation records are kept for 14 days






