FunAudioLLM/CosyVoice
Multilingual text-to-speech model with zero-shot capabilities
View on index · View in 3D Map
Related repos
- Audio language model for voice interactions
- multilingual speech recognition and emotion detection toolkit
- AI model for zero-shot speech editing and text-to-speech
- Text-to-speech library with advanced models in 17 languages (legacy models in 1100+), and tools for custom voice training
- Production-ready text-to-speech API with multiple voices and a real-time dashboard
- open source audio model for expressive speech and voice cloning
- Open-source 1.2B parameter AI for zero-shot voice cloning (American/British accents), emotional English TTS, cross-lingual synthesis
- End-to-end speech-to-speech foundation model
- open-weight text-to-speech model for fast, natural voice synthesis
