On October 26, Tencent Hunyuan's simultaneous interpretation large model Hy-SimulMT was released and open-sourced. It supports real-time Chinese-English speech-to-speech translation: speaker audio can be fed into the model in real time, and it listens and translates simultaneously while outputting translated text and speech in sync. It also supports real-time timbre cloning, reproducing the speaker's voice and tone. The model made its debut with a free trial in the Tencent Hy Translation App, and the open-source repository is also available on HuggingFace, ModelScope, and GitHub.