Sound Model

Tencent SmartShadow announced a major upgrade of its voice model, with specific enhancements including more natural and coherent voices, richer intonation and emotion, fewer voice imperfections and better adaptability. The new version of the voice is more natural and coherent, has richer intonation and emotion, reduces the probability of voice defects, and better adapts to different text content and contexts. At the same time, Smart Shadow has also introduced two new free tones, namely, a passionate female voice and a cute and friendly female voice, which are suitable for conversational chatting scenarios. In addition, the sound customization effect has also been upgraded, the sampling rate has been upgraded from 16K to 24K, and users can customize the tones with the same upgraded effect. Overall...