Audio creation model

On July 21st, the byte beat of the Seed team released yesterday, Seed Audio 1.0, which uses a unified framework to model human, audio and environmental voices and to organize the entry of roles, lines, emotions, background and sound with a single instruction. Time control: The model will break the creative intent into a structured time line, currently supporting 100 ms space accuracy. Sound and duration: Supports text or reference audio input, which produces about 2 minutes of audio at a single time and can continue to be extended to maintain the role ' s voice and expression. Multilingual: Chinese, English, Japanese, Korean,..