Tencent Hunyuan has released and open-sourced Hy-SimulMT, a simultaneous interpretation model that turns Chinese speech into English speech, and English into Chinese, while the speaker is still talking. It clones the speaker's voice in real time, so listeners hear the translation in something close to the original voice. The model is live first in the Hy Translate app, where it is free to use, according to IT Home and the project's GitHub and Hugging Face pages.
The key number is latency. Tencent measures it with StreamLAAL, a standard metric for streaming translation lag, and reports about 3 seconds on the long-form RealSI benchmark, the lowest among the systems it compared. The project notes that StreamLAAL is not the same as the time until the first translated speech is heard. IT Home, for comparison, puts the typical lag of professional human interpreters at 4 to 5 seconds.
On quality, Hy-SimulMT's GEMBA score on long-form speech beat the open models in the comparison and four of the five commercial APIs tested. On short-form sets it scored 90.3 on FLEURS, 75.5 on CoVoST2, 81.2 on ACL6060 and 84.7 on RealSI-Sentence, the last being the highest of every listed system.
The team also compared the model with human interpreters on 18 recordings of about six minutes each, recorded from September 2026 onward across 10 domains. Six interpreters took part, three holding China's top CATTI Level 1 interpreting certificate and three holding Level 2, and the best result from each level was used. Tencent calls this a small-scale assessment. Wang Weiwei, vice dean of the School of Interpreting and Translation Studies at Guangdong University of Foreign Studies, said in remarks published with the release that the system speaks first and corrects itself afterward, much like a human interpreter, and that AI interpreting is moving from helping people understand toward usable communication in low-risk settings.
The released model is a 30B-A3B mixture-of-experts system, with FP8 and GGUF builds and an Interleave variant that also outputs the source transcript. The Hugging Face card lists an Apache 2.0 license. Tencent ships two tools with it: SimulInfer, a serving stack built on vLLM with a web interface, a WebSocket API and optional text-to-speech, and SimulTrain for further training on domain data. Support in llama.cpp has not yet been merged.
The release follows Hunyuan's earlier open translation models and moves the line from text into live speech, the setting where delay matters most.
SEE ALSO: Tencent Hunyuan Open-Sources Hy Memory 2.0, Adding Working and Code Memory for AI Agents · Tencent Hunyuan Open-Sources Translation Model 1.5: Runs on 1GB Phone Memory, Outperforms Commercial APIs