Tencent Mixuan has released the real-time speech model Hy Realtime: it can speak, sing, and also call tools, and has been launched on Yuanbao voice calls, Tencent Customer Service, and other platforms.
Tencent Mixuan has released the real-time speech model Hy Realtime, which has excellent performance in basic conversational abilities such as speech understanding, command following, and anthropomorphic expression, while also adding new Agentic tool calls and singing capabilities. Hy Realtime has already been launched in Yuanbao voice calls, Tencent Customer Service, and other products, and will also be launched on Tencent Cloud in the near future, providing API services to the public.
Same story1 other outlet also reported this
- ITHome · AI··First·Reading now
Tencent Mixuan has released the real-time speech model Hy Realtime: it can speak, sing, and also call tools, and has been launched on Yuanbao voice calls, Tencent Customer Service, and other platforms.
- 36Kr · AI··+18 min
Tencent Mixuan has released a new real-time speech model, Hy Realtime.
Adds:36Kr mentions the context window of 1M; API at $2.00 per million input tokens
In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary
Source: ITHome · AI · ithome.com