The Alibaba Tongyi Laboratory voice team announced that its open-source voice generation model CosyVoice has been upgraded to version 2.0. This upgrade marks significant progress in voice generation technology in terms of accuracy, stability, and natural experience. CosyVoice 2.0 achieves bidirectional streaming voice synthesis through the integration of offline and streaming modeling techniques, allowing for a first-package synthesis delay of up to 150ms, thereby significantly improving the responsiveness of voice synthesis.

Alibaba's latest CosyVoice speech synthesis model and SenseVoice speech recognition model together form the FunAudioLLM framework, aimed at enhancing human-computer interaction experience. CosyVoice, with its realistic voice generation capability, can mimic voices of different genders, ages, and personalities, adding emotions and styles while even simulating natural features such as laughter, coughing, and breathing. SenseVoice focuses on high-precision multilingual speech recognition, emotion detection, and audio event detection, supporting over 50 languages.