# Tencent releases Hy-SimulMT, a real-time Chinese-English simultaneous translation model

> Original title: tencent/Hy-SimulMT-30B-A3B-Interleave

- Source: Tencent · new models on Hugging Face
- Published: 2026-10-22T07:44:33.000Z
- Bad Influence: https://badinfluence.news/items/j9wpsdc28kto093b40nd37z1k
- Original: https://huggingface.co/tencent/Hy-SimulMT-30B-A3B-Interleave

## Summary

Tencent Hunyuan has released Hy-SimulMT, a real-time simultaneous translation model for bidirectional Chinese-English speech-to-speech translation with real-time voice cloning. In the RealSI long-form audio evaluation, the company reports a StreamLAAL of about 3 seconds, the lowest among the systems shown, and a GEMBA score above the compared open-source models and four of five commercial APIs. The model is available on Hugging Face and ModelScope in several variants, including FP8 and GGUF formats.

## Why it matters

The release page documents latency and quality results against open-source models and commercial APIs, plus the setup path, helping readers judge real-time Chinese-English translation.