Tencent Open-Sources Hy-SimulMT: 3s Latency Beats Human Interpreters

1 reports archived1 independent sourcesupdated 10/26/2026, 22:09:04

Synthesis & Latest Updates

1 Sources Cross-Validated

Tencent has open-sourced Hy-SimulMT, a simultaneous interpretation LLM supporting real-time Chinese-English speech-to-speech translation with voice cloning. With a latency of ~3 seconds, it outperforms the average human interpreter and matches or exceeds expert-level translation quality. The model is now available for free via the Tencent Hy Translation app.

LATEST/Tencent has open-sourced Hy-SimulMT, a simultaneous interpretation LLM supporting real-time Chinese-English speech-to-speech translation with voice cloning. With a latency of ~3 seconds, it outperforms the average human interpreter and matches or exceeds expert-level translation quality. The model is now available for free via the Tencent Hy Translation app.

Hourly heat curve

3 fully observed hours

Now

11.2

Peak

11.823:00

24h change

–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first

IT之家 · 智能时代T2Oct 26, 22:09·85 pts
Tencent Open-Sources Hy-SimulMT: 3s Latency Beats Human Interpreters
- Hy-SimulMT achieves ultra-low latency of ~3 seconds, faster than professional human interpreters (4-5 seconds)
- Translation quality on RealSI and custom multi-domain datasets exceeds mainstream open-source models and some commercial APIs
- Supports real-time voice cloning to highly replicate speaker tone and voice characteristics
View Related Reports & Analysis Original Source