January 20th, Jinshi data, the real-time voice large model of Bean has officially launched today and is fully open in the Bean app. The real-time voice large model of Bean is an integrated model of voice understanding and generation, realizing end-to-end voice conversation. Compared with the traditional cascade mode, it shows amazing performance in voice expression, control, and emotional continuity, and has the characteristics of low latency and the ability to interrupt the conversation at any time.
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Real-time voice large model for bean bag online
January 20th, Jinshi data, the real-time voice large model of Bean has officially launched today and is fully open in the Bean app. The real-time voice large model of Bean is an integrated model of voice understanding and generation, realizing end-to-end voice conversation. Compared with the traditional cascade mode, it shows amazing performance in voice expression, control, and emotional continuity, and has the characteristics of low latency and the ability to interrupt the conversation at any time.