Lalo v0.1.0 - Initial Release
High-Performance EPUB to Audiobook Converter
Transform your EPUB ebooks into professional audiobooks using state-of-the-art Qwen3-TTS technology with GPU acceleration.
🎉 First Stable Release
This is the first stable release of Lalo, featuring a complete, production-ready EPUB to audiobook conversion pipeline with advanced optimizations and comprehensive features.
✨ Key Features
Multi-Language Support
- 10 Languages: Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
- Auto-Detection: Automatically detects language per chapter
- Native Voices: 9 voice profiles with native language specialization
Premium Voice Control
- 9 High-Quality Speakers: Covering various genders, ages, languages, and dialects
- Natural Language Instructions: Control tone, pace, emotion, and style with simple phrases
- Genre Optimization: Tailored narration styles for fiction, non-fiction, mystery, children's books, poetry, and more
Advanced Audio Processing
- Multiple Formats: Export to WAV (lossless), MP3 (compressed), or M4B (audiobook with chapters)
- Chapter Markers: M4B format includes navigable bookmarks for easy navigation
- High Quality: 24kHz sample rate, 192k bitrate for crystal-clear audio
🚀 Quick Start
Installation
From PyPI (Recommended)
# Install the package
pip install lalo-tts
# Optional: Install FlashAttention2 for faster inference
pip install flash-attn --no-build-isolationFrom Source (Development)
# Clone the repository
git clone https://github.com/willianpaixao/lalo.git
cd lalo
# Install in development mode
pip install -e .
# Optional: Install FlashAttention2 for faster inference
pip install flash-attn --no-build-isolationBasic Usage
# Convert entire book with defaults
lalo convert mybook.epub
# Choose specific speaker and chapters
lalo convert mybook.epub --speaker Vivian --chapters 1-10
# Create M4B audiobook with chapter markers
lalo convert mybook.epub --format m4b --output audiobook.m4b
# Add voice instructions for specific narration style
lalo convert novel.epub --instruct "Narrate dramatically with emotion"
# Process large books with streaming mode
lalo convert longbook.epub --streaming🛠️ System Requirements
Hardware
- GPU: NVIDIA GPU with CUDA support (required)
- RAM: 8+ GB recommended (16+ GB for large books without streaming)
- Storage: ~5 GB for model weights
Software
- Python: 3.12 or higher
- CUDA: Compatible CUDA drivers
- ffmpeg: Required for MP3 and M4B export
Full Changelog: This is the initial release - all features are new!
Download: See the assets below or clone with git clone --branch v0.1.0
Enjoy converting your EPUB books to professional audiobooks! 🎧📚