FunAudioLLM is an open-source project for voice understanding and generation models from Tongyi Speech Lab, Alibaba Group. The project includes the demo homepage for each subproject of FunAudioLLM.
SenseVoice & CosyVoice: https://funaudiollm.github.io
CosyVoice2.0: https://funaudiollm.github.io/cosyvoice2
MinMo: https://funaudiollm.github.io/minmo
InspireMusic: https://funaudiollm.github.io/inspiremusic
Fun-ASR: https://funaudiollm.github.io/funasr
Fun-Audio-Chat: https://funaudiollm.github.io/funaudiochat