# xunbu/docutranslate

文档（小说、论文、字幕）翻译工具（支持 pdf/word/excel/json/epub/srt...）Document (Novel, Thesis, Subtitle) Translation Tool (Supports pdf/word/excel/json/epub/srt...)

Repository: https://github.com/xunbu/docutranslate
Canonical: https://ross.abutalabs.com/products/docutranslate
Language: Python
License: MPL-2.0
License Family: copyleft
Topics: llm, pdf-converter, pdf-translator, translate, file-transla
Last push: 2026-09-02T02:39:35+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 80, longevity 34
- inputs: {"age_days": 482, "days_push": 0, "days_rel": 54, "gap_med": 3, "n_releases_24m": 64}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1285, forks 184 (observed 2026-09-03T02:15:20.723956+00:00)

## What it is
DocuTranslate is a lightweight local document translation tool powered by large language models, supporting formats such as pdf, docx, xlsx, md, , epub, srt, and ass. It offers a web UI and RESTful API, automatic glossary generation, PDF table/formula/code recognition via mineru, and format-preserving Word/Excel translation.

## Use cases
- translate a novel from epub while keeping terminology consistent
- translate academic papers in pdf with tables and formulas
- translate srt subtitles for a video
- translate a docx report preserving formatting
- translate specific values inside a  file
- batch translate documents via a restful api
- run a local translation service for multiple users on a lan

## When to choose
- you need LLM-based translation of whole documents across many file formats
- you want format preservation for docx/xlsx or glossary-consistent term translation
- you prefer a self-hosted tool with a web UI and API rather than pasting text into a chatbot

## When to avoid
- you need exact PDF layout preservation, since PDFs are converted to markdown and lose layout
- you only need machine translation without LLMs or want an offline non-AI translator
- you need to translate legacy .doc or .xls files

## Facets
- artifact type: application
- maturity: active
- function: nlp, llm-inference, pdf, ocr, web-framework, http-server
- domain: pdf, files, large-language-models, developer-tools
- platform: python, cross-platform, self-hosted, windows
- tags: document-translation, file-translation, glossary, subtitle-translation, epub, srt, docx, xlsx, mineru, web-ui, restful-api, natural-language-processing, localization, web-server, macos

## Member repositories
- xunbu/docutranslate (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:20.723956+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 2026-08-30T05:02:34.558476+00:00, confidence not recorded.
  - readme: https://github.com/xunbu/docutranslate (fetched 2026-09-03T02:15:20.723956+00:00, sha 306f0ad31f46)
- Data as of 2026-08-30T08:39:29.467469+00:00.