All AI tools by developer: Tongyi Lab

Gummy is a real-time, end-to-end voice translation model supporting over a dozen languages with sub-500ms latency and domain-aware translation tuning.

CosyVoice 2.0 is an open-source, high-fidelity streaming text-to-speech model that delivers ultra-low-latency, multilingual, emotionally expressive, and speaker-controllable voice synthesis.