88Z AI, 27 October — Tencent Hunyuan has open-sourced Hy-SimulMT, a simultaneous interpretation model supporting real-time Chinese-English translation and voice cloning. With a response time of about 3 seconds, it is faster than human interpreters and achieves expert-level quality, outperforming mainstream open-source models and many commercial APIs.
At a glance
- Supports real-time Chinese-English translation and voice cloning with ~3s response
- Translation quality matches human experts, surpassing mainstream open-source models and commercial APIs
The update
Tencent Hunyuan has officially open-sourced Hy-SimulMT, a large model for simultaneous interpretation. It supports real-time mutual translation between Chinese and English speech, allowing for translation while listening, and can clone the speaker's voice in real time to accurately restore the original sound and tone. In terms of performance, Hy-SimulMT has a measured response time of approximately 3 seconds, which is faster than the average 4 to 5 seconds of human professional interpreters. Multiple evaluations indicate that the model's translation quality reaches the level of human simultaneous interpretation experts, outperforming both mainstream open-source models and most commercial API services.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 腾讯混元Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.