TranslateBooksWithLLMs
Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral, DeepSeek, Poe or OpenRouter. Preserves formatting. Resumes where you
What is 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.
Overview of TranslateBooksWithLLMs
What it is
TranslateBooksWithLLMs (TBL) is a desktop application that translates books, subtitles, and documents using AI. It supports both local and cloud-based language models. The app accepts files in EPUB, SRT, DOCX, PDF, and TXT formats.
Key features
- No file size limit: processes documents of any length using an intelligent chunking system that preserves context between segments.
- Perfect preservation: EPUB formatting, styles, and structure remain intact; SRT timecodes stay synchronized; all tags, timestamps, and formatting details are preserved.
- Resume anytime: an automatic checkpoint system saves progress so interrupted translations can be resumed exactly where they left off.
- Reusable writing styles: extract a style preset from sample books or write one manually, then apply it consistently across every chunk.
- Auto glossary & style: when no glossary or preset is provided, the app derives both from the document being translated with one extra LLM call each before the job starts.
- PDF support: text PDFs are translated into a new reflowed PDF that keeps headings, paragraphs, lists, images, ruled tables, paragraph colours, background boxes, and font family (serif, sans-serif, monospace); original page layout is not preserved; scanned PDFs (no OCR) are not supported; multi-column layouts are best effort; the refinement pass is not available for PDF yet.
Use cases
Translating full-length books, subtitles, and documents while preserving original formatting. Resuming interrupted translations without losing progress. Applying a consistent writing style across an entire translation. Using local AI models for privacy or cloud models for convenience.
Getting started
Download the release for your platform from the repository, extract the archive, and run the executable. On first launch, open http://localhost:5000 in your browser and choose a translation provider. For local use, install Ollama and pull a model (e.g., ollama pull qwen3:14b). For cloud use, paste an API key from one of the supported providers. Alternatively, install from source: bash git clone https://github.com/hydropix/TranslateBooksWithLLMs.git cd TranslateBookWithLLM ollama pull qwen3:14b # Windows start.bat # Mac/Linux chmod +x start.sh && ./start.sh The web interface opens at http://localhost:5000.
License and pricing
The project is licensed under AGPL-3.0 and is open source with no pricing.
Based on the project's public README and repository metadata.