APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
newsOpen SourceAudio

Tencent's Hy-SimulMT Translates Chinese and English Before Speakers Finish Talking

Tencent open-sourced a 30B MoE model for live Chinese-English speech interpretation, hitting roughly 3-second latency with real-time voice cloning.

Tencent's Hy-SimulMT Translates Chinese and English Before Speakers Finish Talking
Source
Tencent Hy
Published
Author
AlphaSignal Newsroom
Read
1 min read

Tencent open-sourced a 30B MoE model for live Chinese-English speech interpretation, hitting roughly 3-second latency with real-time voice cloning.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Ant Group's Ming-3.0 Tops Open-Source Voice Charts With Five Speech Models
AlphaSignal · model

Ant Group's Ming-3.0 Tops Open-Source Voice Charts With Five Speech Models

Ant Group's Ming-3.0 Beats Larger Voice Models at Just 0.5B Parameters
Artificial Analysis · news

Ant Group's Ming-3.0 Beats Larger Voice Models at Just 0.5B Parameters

A Slovak XLS-R Model Quietly Hits 860,000 Monthly Downloads on Hugging Face
AlphaSignal · model

A Slovak XLS-R Model Quietly Hits 860,000 Monthly Downloads on Hugging Face