Alibaba Tongyi Laboratory releases the open-source speech generation model FunAudioLLM, enhancing multi-language audio generation and recognition capabilities through CosyVoice and SenseVoice models.

⌘K

F

Alibaba Tongyi Laboratory releases the open-source speech generation model FunAudioLLM, enhancing multi-language audio generation and recognition capabilities through CosyVoice and SenseVoice models. | BestBlogs.dev