Tencent Meeting Rolls Out 'AI Simultaneous Interpretation': Replicates User's Vocal Tone with Sub-3-Second Latency
7 hour ago / Read about 0 minute
Author:小编   

On May 21, 2026, Tencent Meeting proudly unveiled its innovative AI simultaneous interpretation feature, which initially supports seamless mutual translation between Chinese and English. Boasting a latency of under 3 seconds, this cutting-edge functionality ensures near-real-time speech and translation, effectively overcoming the challenges of significant delays and disjointed exchanges that have long plagued traditional simultaneous interpretation methods.

Participants have the autonomy to activate AI simultaneous interpretation at their convenience, choose their desired language, fine-tune the volume balance between the interpreted and original audio streams, and effortlessly adapt to a wide range of settings, from formal business meetings to casual gatherings.

A standout feature of this technology is its ability to replicate the user's vocal tone, giving the impression that the speaker is fluently articulating their thoughts in a foreign language. Moreover, AI simultaneous interpretation seamlessly integrates with text transcription and in-meeting subtitles, enabling users to simultaneously listen, translate, view, and record crucial information.

To get started, simply click on 'Tools' followed by 'Applications' after joining a meeting, and then select the 'Simultaneous Interpretation in Progress' icon to access the settings and customize your experience.