DigitalPhonetics/IMS-Toucan
Text-to-speech synthesis for over 7000 languages
View on index · View in 3D Map
Related repos
- Synthesizes speech in 7000 languages
- open-weight text-to-speech model for fast, natural voice synthesis
- zero-shot text-to-speech with voice cloning for English and Chinese
- Modular text-to-speech system with multilingual support
- Converts text to speech across languages
- Text-to-speech library with advanced models in 17 languages (legacy models in 1100+), and tools for custom voice training
- speech recognition, synthesis, and audio tools for many platforms
- Text-to-speech on CPUs with voice cloning
- Real-time transcription using Faster-Whisper
- LLM-powered text-to-speech with voice cloning and bilingual support
