BabelDOC
Yet Another Document Translator
Decision gist · record as of 2026-08-14
Yes, if you need to translate PDFs and can accept the AGPL-3.0 license terms and the large dependency footprint. The package is actively maintained, has no known vulnerabilities, and offers both CLI and library modes. No, if you require a permissive license, need production-ready support for non-English-to-Chinese pairs, or want to avoid the 33-dependency install. Yes-with-conditions if you plan to embed it: verify that the Python API is stable for your use case, as the CLI is noted as primarily for debugging.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later (and <3.14).
- An OpenAI API key or alternative translation service configuration is needed to actually translate documents.
- Low install friction with a pure Python wheel.
License · maintenance · safety
AGPL-3.0 (agpl) — Licensed under AGPL-3.0. Any modifications or derivative works must be released under the same license and source made available; using this in a proprietary product without disclosure is not permitted.
last release 2026-07-16 (29 days) · last repo commit 2026-08-05 · 9,349 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 74,296 downloads/mo, #14,852 on PyPI
Alternatives
Verify before relying
pip install BabelDOC
babeldoc --openai --openai-model "gpt-4o-mini" --openai-base-url "https://api.openai.com/v1" --openai-api-key "your-api-key-here" --files example.pdf- Whether non-English-to-Chinese translation pairs are production-ready or experimental.
- Performance characteristics and typical translation latency for multi-page documents.
- Whether the 1000 free pages/month quota mentioned for the online service applies to self-hosted deployments.
- Stability and compatibility of the CLI versus embedding the package as a library in other applications.
What it is and what it does
BabelDOC is a PDF translation and bilingual comparison library designed primarily to translate scientific papers from English to Chinese while preserving layout and formatting. It can produce side-by-side or alternating-page dual PDFs showing original and translated text. The package is built on a large stack of ML and computer vision dependencies (onnxruntime, opencv, scikit-learn, etc.) to handle PDF parsing, text extraction, layout analysis, and rendering. It exposes both a command-line interface for simple translation tasks and a Python API for embedding into other programs.
The package is actively maintained and young (first release February 2025), with an AGPL-3.0 license that requires source disclosure for any modifications. It integrates with external translation services (primarily OpenAI's API) and supports multiple language pairs, though English-to-Chinese is the primary focus and other directions are noted as untested. The 33 runtime dependencies mean a substantial first install, but the wheel distribution keeps setup friction low.
Use it for
- Translate a batch of research papers from English to Chinese for reading alongside the original.
- Embed PDF translation into a reference management tool like Zotero via the Python API.
- Self-host a document translation service with custom translation backends using the library's modular design.
- Extract and translate text from scanned PDFs using OCR workaround modes for documents with poor text layers.
- Generate dual-language PDFs for academic collaboration where both original and translated versions are needed.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to translate PDFs and can accept the AGPL-3.0 license terms and the large dependency footprint.
The package is actively maintained, has no known vulnerabilities, and offers both CLI and library modes. No, if you require a permissive license, need production-ready support for non-English-to-Chinese pairs, or want to avoid the 33-dependency install. Yes-with-conditions if you plan to embed it: verify that the Python API is stable for your use case, as the CLI is noted as primarily for debugging.
Install
babeldoc on PyPI
Before you install
Low install friction with a pure Python wheel. Active maintenance—last commit 2026-08-05, first release 2025-02-11. Carries 33 runtime dependencies including heavy ML/CV stacks (onnxruntime, opencv-python-headless, scikit-learn), which will pull in substantial binary artifacts on first install.
Requires Python 3.10 or later (and <3.14). An OpenAI API key or alternative translation service configuration is needed to actually translate documents.
License in practice
Licensed under AGPL-3.0. Any modifications or derivative works must be released under the same license and source made available; using this in a proprietary product without disclosure is not permitted.
Quickstart
pip install BabelDOC
babeldoc --openai --openai-model "gpt-4o-mini" --openai-base-url "https://api.openai.com/v1" --openai-api-key "your-api-key-here" --files example.pdfVerify before relying
- Whether non-English-to-Chinese translation pairs are production-ready or experimental.
- Performance characteristics and typical translation latency for multi-page documents.
- Whether the 1000 free pages/month quota mentioned for the online service applies to self-hosted deployments.
- Stability and compatibility of the CLI versus embedding the package as a library in other applications.
Package facts
| License | AGPL-3.0 agpl |
| Python support | Supports the current Python release <3.14,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 33 packagesbitstringchardetcharset-normalizerconfigargparsecryptographyfreetype-pyhttpxhuggingface-hubhyperscanlevenshteinmsgpacknumpyonnxonnxruntimeopenaiopencv-python-headlessorjsonpeeweepsutilpydanticpymupdfpyzstdrichrtreescikit-imagescikit-learnscipytenacitytiktokentoml |
| Maintenance | Actively maintained 29 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 74,296 / month, #14,852 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Operating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: babeldoc-0.6.4-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “PDF translation”
- BabelDOCBabelDOC translates PDF documents between languages, primarily…
- deep-translatorTranslates text between languages using multiple free translation…
- aspose-wordsAspose.Words for Python is a document processing library that lets…
Give your agent the search over MCP, or paste the wish link into any chat.
More Linguistic packages
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
tiktoken is a fast BPE tokenizer that converts text into token sequences compatible with OpenAI models, supporting multiple encoding schemes including o200k_base and model-specific encodings.
Install it if you work with OpenAI APIs or need to understand token boundaries in GPT-family models.
Detects character encoding and language in byte sequences with high accuracy, supporting 99 encodings and returning confidence scores, language tags, and MIME types.
Install it if you need to detect character encoding or language in byte data; the rewrite makes it substantially faster and more accurate than its predecessors.
Converts Unicode text to ASCII by transliterating non-ASCII characters into their closest ASCII equivalents, with no runtime dependencies.
However, if transliteration quality or ongoing maintenance matters, consider unidecode instead despite its GPL-only license.
Lark is a parsing library that builds abstract syntax trees from context-free grammars, supporting multiple parsing algorithms (Earley, LALR(1), CYK) with automatic line and column tracking.
Python bindings to the tree-sitter parsing library, enabling incremental parsing and syntax tree analysis for source code.
See also azure-ai-translation-document · translate · deep-translator · prosemirror · translators · deepl · spire-doc · marker-pdf · google-cloud-translate · libretranslatepy