CosyVoice 3.0 — LingPick
Alibaba Tongyi Lab's latest open-source speech synthesis model. Version 3.0 supports stronger voice cloning, emotion control, and streaming inference. Audio quality near human — the benchmark for open-source TTS.
Alibaba Tongyi Lab's latest open-source speech synthesis model. Version 3.0 supports stronger voice cloning, emotion control, and streaming inference. Audio quality near human — the benchmark for open-source TTS.