@cevenif: 还在一段段复制粘贴翻译电子书？你可能已经浪费了大量时间。发现一个开源神器，直接把整本书丢进去就完事了：TranslateBookWithLLM 支持 EPUB 电子书、SRT 字幕、DOCX 文档、纯文本等常见格式本地 Ollama …

X AI KOLs Timeline 2026/06/09 09:46 工具

open-source translation-tool ebook llm ollama epub desktop-app

摘要

TranslateBookWithLLM 是一个开源桌面应用，支持使用本地 Ollama 或云端 API 翻译 EPUB、SRT、DOCX 等格式的文档，保留原始排版并支持断点续传。

还在一段段复制粘贴翻译电子书？你可能已经浪费了大量时间。发现一个开源神器，直接把整本书丢进去就完事了：TranslateBookWithLLM 支持 EPUB 电子书、SRT 字幕、DOCX 文档、纯文本等常见格式本地 Ollama 模型或 Gemini、OpenAI、DeepSeek 等云端 API 随便选智能分块处理，上下文连贯不错乱原有排版结构和格式基本都能保住再也不用忍受复制粘贴丢格式的折磨了，大规模翻译文档就该这么搞。 https://github.com/hydropix/TranslateBooksWithLLMs…

查看原文

查看缓存全文

缓存时间: 2026/06/09 12:46

还在一段段复制粘贴翻译电子书？你可能已经浪费了大量时间。

发现一个开源神器，直接把整本书丢进去就完事了：TranslateBookWithLLM

支持 EPUB 电子书、SRT 字幕、DOCX 文档、纯文本等常见格式本地 Ollama 模型或 Gemini、OpenAI、DeepSeek 等云端 API 随便选智能分块处理，上下文连贯不错乱原有排版结构和格式基本都能保住再也不用忍受复制粘贴丢格式的折磨了，大规模翻译文档就该这么搞。 https://github.com/hydropix/TranslateBooksWithLLMs…

hydropix/TranslateBooksWithLLMs

Source: https://github.com/hydropix/TranslateBooksWithLLMs

TBL - Translate Books with LLMs

A desktop app that translates books, subtitles, and documents with AI - local or cloud. Drop a file, pick a language, get the result.

Formats: EPUB, SRT, DOCX, TXT

No size limit. Process documents of any length - from a single page to thousand-page novels. The intelligent chunking system handles unlimited content while preserving context between segments.
Perfect preservation. Your documents come out exactly as they went in: EPUB formatting, styles, and structure remain intact. SRT timecodes stay perfectly synchronized. Every tag, every timestamp, every formatting detail is preserved.
Resume anytime. Interrupted translation? Pick up exactly where you left off. The checkpoint system saves progress automatically.

Translation Quality Benchmarks - Find the best model for your target language.

Quick Start

Download the release for your platform (buttons above), or grab it from the releases page.
Extract the archive.
Run TranslateBook.exe (Windows) or ./TranslateBook (macOS).
Open http://localhost:5000 in your browser.

That’s it. On first launch, you choose a translation provider:

Free & local - Install Ollama and pull a model (e.g. ollama pull qwen3:14b). Nothing leaves your machine.
Cloud (often free tier available) - Paste an API key from one of the providers below.

Note: First run creates a TranslateBook_Data folder with your settings.

macOS: On first launch, go to System Settings > Privacy & Security and click Open Anyway.

Providers

Provider	Type	Get started
DeepSeek	Cloud	platform.deepseek.com
Gemini	Cloud	Google AI Studio
Mistral	Cloud	console.mistral.ai
NVIDIA NIM	Cloud	build.nvidia.com
Ollama	Local	ollama.com
OpenAI	Cloud	platform.openai.com
OpenAI-Compatible	Local (llama.cpp, LM Studio, vLLM, LocalAI…)	Point to your server’s endpoint
OpenRouter	Cloud (200+ models)	openrouter.ai/keys
Poe	Cloud (multi-model)	poe.com/api_key

See docs/PROVIDERS.md for detailed setup instructions.

Troubleshooting

Problem	Solution
Ollama won’t connect	Check Ollama is running, test `curl http://localhost:11434/api/tags`
Model not found	Run `ollama list`, then `ollama pull model-name`

See docs/TROUBLESHOOTING.md for more solutions.

Advanced

Install from source

Prerequisites: Python 3.8+, Ollama, Git

git clone https://github.com/hydropix/TranslateBooksWithLLMs.git
cd TranslateBookWithLLM
ollama pull qwen3:14b    # Download a model

# Windows
start.bat

# Mac/Linux
chmod +x start.sh && ./start.sh

The web interface opens at http://localhost:5000.

Command line

# 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

Main options

Option	Description	Default
`-i, --input`	Input file	Required
`-o, --output`	Output file	Auto: `{name} ({lang}).{ext}`
`-sl, --source_lang`	Source language	English
`-tl, --target_lang`	Target language	Chinese
`-m, --model`	Model name	qwen3:14b
`--provider`	ollama/openrouter/openai/gemini/mistral/deepseek/poe/nim	ollama
`--parallel`	Chunks translated concurrently (cloud only; Ollama stays at 1)	1
`--text-cleanup`	OCR/typographic cleanup	disabled
`--refine`	Second pass for literary polish	disabled
`--tts`	Generate audio (Edge-TTS)	disabled

See docs/CLI.md for all options (TTS voices, rates, formats, etc.).

Configuration (.env)

Copy .env.example to .env and edit:

# Provider
LLM_PROVIDER=ollama

# Ollama
API_ENDPOINT=http://localhost:11434/api/generate
DEFAULT_MODEL=qwen3:14b

# API Keys (if using cloud providers)
OPENROUTER_API_KEY=sk-or-v1-...
OPENAI_API_KEY=sk-...
GEMINI_API_KEY=...
MISTRAL_API_KEY=...
DEEPSEEK_API_KEY=...
POE_API_KEY=...
NIM_API_KEY=...

# Performance
REQUEST_TIMEOUT=900
MAX_TOKENS_PER_CHUNK=450     # Token-based chunking (default: 450 tokens)
PARALLEL_TRANSLATIONS=1      # Concurrent chunks (cloud only; Ollama stays at 1)

Faster on cloud providers? Set PARALLEL_TRANSLATIONS (or --parallel N, or the “Parallel requests” field in the web UI) above 1 to translate several chunks at once. Local providers (Ollama) ignore it since a single instance serializes requests. Higher values are faster but can hit provider rate limits.

Multiple API keys? Any *_API_KEY variable accepts a comma-separated list (e.g. GEMINI_API_KEY=key1,key2,key3). The system rotates between keys automatically when one hits a rate limit - useful to chain free-tier accounts. See docs/API_KEY_ROTATION.md.

Long jobs? Get a push notification on your phone (via ntfy), Discord, Slack, gotify, or any HTTP endpoint when a translation finishes. Set NOTIFY_WEBHOOK_URL in .env. See docs/NOTIFICATIONS.md.

Docker

docker build -t translatebook .
docker run -p 5000:5000 -v $(pwd)/translated_files:/app/translated_files translatebook

See docs/DOCKER.md for more options.

Documentation

Guide	Description
docs/PROVIDERS.md	Detailed provider setup (Ollama, LM Studio, OpenRouter, OpenAI, Gemini)
docs/API_KEY_ROTATION.md	Use multiple API keys per provider with automatic failover on rate-limit
docs/NOTIFICATIONS.md	Webhook notifications on completion (ntfy, gotify, Discord, Slack, custom)
docs/GLOSSARY.md	Force consistent term translations across a book (Web UI + CLI, auto-extract via NER)
docs/CLI.md	Complete CLI reference
docs/TROUBLESHOOTING.md	Problem solutions
docs/DOCKER.md	Docker deployment guide