TranslateBooksWithLLMs

What it is

A desktop application that translates books, subtitles, and documents using AI. It supports formats EPUB, SRT, DOCX, TXT and can run locally with Ollama or via cloud providers. It preserves formatting and can resume translation from a checkpoint. It includes a feature to derive a writing style preset and an auto glossary & style mechanism.

How it works

The app offers a Quick Start workflow: download the release, extract, run TranslateBook.exe (Windows) or ./TranslateBook (macOS), then open http://localhost:5000. On first launch, you choose a translation provider (local Ollama or cloud providers such as OpenAI, Gemini, Mistral, OpenRouter, Poe, DeepSeek, Nim). It supports chunking for long documents and preserves EPUB formatting, SRT timecodes, and other formatting details. Configuration includes a .env file for provider, API keys, endpoint, and performance settings such as PARALLEL_TRANSLATIONS. Documentation includes multiple provider guides and a CLI example set for various providers. The CLI examples show how to translate with different providers and specify models and target languages.

Getting started

• Download the appropriate release for your platform from the releases page or the provided buttons.
• Extract the archive.
• Run TranslateBook.exe (Windows) or ./TranslateBook (macOS).
• Open http://localhost:5000 in your browser.
• On first run, select a provider (local Ollama or cloud).

Command line usage examples (from README):

# Basic (auto-generates "book (Chinese).epub")
python translate.py -i book.epub -sl English -tl Chinese

# With OpenRouter
python translate.py -i book.txt --provider openrouter \
    --openrouter_api_key YOUR_KEY -m anthropic/claude-sonnet-4 -tl French

# With OpenAI
python translate.py -i book.txt --provider openai \
    --openai_api_key YOUR_KEY -m gpt-4o -tl French

# With Gemini
python translate.py -i book.txt --provider gemini \
    --gemini_api_key YOUR_KEY -m gemini-2.0-flash -tl French

# With Mistral
python translate.py -i book.txt --provider mistral \
    --mistral_api_key YOUR_KEY -m mistral-large-latest -tl French

# With DeepSeek
python translate.py -i book.txt --provider deepseek \
    --deepseek_api_key YOUR_KEY -m deepseek-v4-pro -tl French

# With Poe
python translate.py -i book.txt --provider poe \
    --poe_api_key YOUR_KEY -m Claude-Sonnet-4 -tl French

# With NVIDIA NIM
python translate.py -i book.txt --provider nim \
    --nim_api_key YOUR_KEY -m meta/llama-3.1-8b-instruct -tl French

# With local OpenAI-compatible server (llama.cpp, LM Studio, vLLM, etc.)
python translate.py -i book.txt --provider openai \
    --api_endpoint http://localhost:8080/v1/chat/completions -m your-model -tl French

Getting started (env and configuration)

• Copy .env.example to .env and edit with provider, API keys, and performance settings (e.g., PARALLEL_TRANSLATIONS, MAX_TOKENS_PER_CHUNK).
• Multiple API keys can be set as comma-separated lists per key variable to enable automatic rotation.
• Notifications can be configured via NOTIFY_WEBHOOK_URL for completion status.

Recent releases

Latest Windows/macOS releases provide executable builds with platform-specific installers and updates (Windows: v1.5.4, macOS: v1.5.2, v1.5.1, v1.5.0, etc.). Each release includes the corresponding binary distribution for Windows or macOS (Intel or Apple Silicon). Older Windows/macOS releases are listed with their install instructions.

Traction

Stars: 2250, Forks: 292, Open issues: 18

Caveats

License: AGPL-3.0