Tencent Hunyuan Releases Hy-SimulMT-30B-A3B for Real-Time Simultaneous Speech Translation

·2026.10.26 17:51

Key point

The model supports bidirectional Chinese-English speech-to-speech translation with voice cloning, outperforming four of five commercial APIs on GEMBA scores.

Details

Tencent Hunyuan released Hy-SimulMT-30B-A3B, a real-time simultaneous translation model supporting bidirectional speech-to-speech translation between Chinese and English.
In the RealSI long-form audio evaluation, the model achieved a StreamLAAL of approximately 3 seconds, the lowest among compared systems.
Its GEMBA score exceeded those of compared open-source models and four of the five commercial APIs.
The model features real-time voice cloning to preserve speaker vocal characteristics while translating.
GitHub repository provides SimulInfer inference service and SimulTrain training tools; speech output requires a configured TTS service.
Available for use in the Hy Translate App.

tencent real-time-ai speech-to-speech hunyuan simultaneous-translation hy-simulmt

Read originalShare on Threads

This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.

Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.