CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
About CosyVoice
CosyVoice is an open-source multi-lingual large voice generation model designed to facilitate voice synthesis across various languages. It offers comprehensive capabilities for inference, training, and deployment, making it suitable for developers and researchers in the field of natural language processing and artificial intelligence.
CosyVoice — FAQ
What is CosyVoice?+
CosyVoice is a voice AI product — Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
What does CosyVoice do?+
CosyVoice works in Text-to-Speech (TTS) — Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability..
Is CosyVoice open source?+
Yes, CosyVoice is open source (Apache-2.0 license). The source is on https://github.com/FunAudioLLM.
