# funstory-ai/BabelDOC

Yet Another Document Translator

Repository: https://github.com/funstory-ai/BabelDOC
Canonical: https://ross.abutalabs.com/products/babeldoc
Homepage: https://funstory-ai.github.io/BabelDOC/
Language: Python
License: AGPL-3.0
License Family: copyleft
Last push: 2026-08-05T20:40:20+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 96, release rhythm 81, longevity 47
- inputs: {"age_days": 658, "days_push": 28, "days_rel": 48, "gap_med": 0, "n_releases_24m": 210}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9408, forks 779 (observed 2026-08-28T04:10:31.054833+00:00)

## What it is
BabelDOC is a Python library and CLI tool for translating PDF scientific papers with bilingual comparison output. It uses LLM-based translation (e.g., OpenAI models) and is designed to be embedded into other programs or used directly for simple translation tasks.

## Use cases
- translate scientific papers from pdf
- create bilingual pdf documents
- translate academic papers with llm
- batch translate pdf files from the command line
- embed pdf translation into another application
- use pdf translation in zotero

## When to choose
- you need to translate PDF research papers while preserving layout
- you want side-by-side bilingual output of the original and translated text
- you need a Python API or CLI for programmatic PDF translation
- you want a self-hostable alternative to online document translators

## When to avoid
- you need to translate non-PDF formats like Word or EPUB
- you want a polished end-user web app rather than a library or CLI
- you cannot provide an LLM API key or self-hosted translation service
- your PDFs are scanned images without extractable text

## Facets
- artifact type: library
- maturity: active
- function: pdf, nlp, cli, parser
- domain: pdf, developer-tools, education
- platform: python, cli, cross-platform
- tags: pdf-translation, bilingual-comparison, scientific-papers, llm-translation, document-translator, natural-language-processing

## Member repositories
- funstory-ai/BabelDOC (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:31.054833+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:22:10.416139+00:00, confidence not recorded.
  - readme: https://github.com/funstory-ai/BabelDOC (fetched 2026-08-28T04:10:31.054833+00:00, sha befe6689fdfd)
  - homepage: https://funstory-ai.github.io/BabelDOC/ (fetched 2026-08-29T08:22:14.324091+00:00, sha 06e9c1d0b76c)
  - registry_pypi: https://pypi.org/pypi/babeldoc/json (fetched 2026-08-29T08:22:14.333751+00:00, sha 9d4a92f3deb5)
- Data as of 2026-08-30T08:39:29.467469+00:00.