# hydropix/TranslateBooksWithLLMs

Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral, DeepSeek, Poe or OpenRouter. Preserves formatting. Resumes where you left off. No file size limits.

Repository: https://github.com/hydropix/TranslateBooksWithLLMs
Canonical: https://ross.abutalabs.com/products/translatebookswithllms
Homepage: https://github.com/hydropix/TranslateBooksWithLLMs/wiki
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: llm, ollama, translation, local-llm, localization-tool, translation-tool, epub, srt-subtitles, gemini, gemini-api, openai-api, openrouter, lmstudio, docx, poe, mistral, book-translation, deepseek, ebook-translator, epub-translator
Last push: 2026-08-24T21:26:47+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 33
- inputs: {"age_days": 468, "days_push": 9, "days_rel": 9, "gap_med": 0.0, "n_releases_24m": 75}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2334, forks 303 (observed 2026-08-28T04:06:37.952053+00:00)

## What it is
A desktop application that translates full-length books, subtitles, and documents using local or cloud LLMs (Ollama, OpenAI-compatible APIs, Gemini, Mistral, DeepSeek, Poe, OpenRouter). It preserves document formatting, supports EPUB/SRT/DOCX/TXT, has no file size limits, and can resume interrupted translations from checkpoints.

## Use cases
- translate an entire epub novel to another language with an LLM
- translate srt subtitles while keeping timecodes synchronized
- translate long docx documents with no file size limit
- run fully local book translation with ollama for privacy
- resume an interrupted translation where I left off
- keep consistent translation style across a whole book with style presets
- auto-generate a glossary from the document before translating

## When to choose
- you need whole-book or long-document translation with formatting preserved
- you want to use local models via Ollama or LM Studio instead of cloud APIs
- you need checkpoint/resume for very long translation jobs
- you work with EPUB, SRT, DOCX, or TXT files

## When to avoid
- you need real-time or streaming translation of live content
- you need a translation API or library to embed in your own code rather than a standalone app
- you need machine translation without LLM costs or setup
- you need formats beyond EPUB, SRT, DOCX, and TXT

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, internationalization, nlp, gui
- domain: large-language-models, files, pdf
- platform: windows, cross-platform, python, self-hosted
- tags: book-translation, epub, srt-subtitles, docx, ollama, openai-compatible, glossary, style-presets, checkpoint-resume, local-llm, localization, natural-language-processing, macos

## Member repositories
- hydropix/TranslateBooksWithLLMs (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.952053+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 2026-08-30T02:37:46.042093+00:00, confidence not recorded.
  - readme: https://github.com/hydropix/TranslateBooksWithLLMs (fetched 2026-08-28T04:06:37.952053+00:00, sha c4fef26e0358)
  - homepage: https://github.com/hydropix/TranslateBooksWithLLMs/wiki (fetched 2026-08-29T10:18:21.540176+00:00, sha e97adad860d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.