Event ·Official first-hand

Meta发布Muse Voice Transcribe模型

Meta Superintelligence Labs本周发布Muse Voice Transcribe模型，将语音识别、说话人分离和端点检测三个功能整合为一个自回归模型。该模型专为实时流式语音处理设计，解决了传统语音系统中多个模型交接带来的延迟和故障点问题。Muse Voice Transcribe通过单一模型完成三项任务，提高了语音处理的效率和可靠性。

Current read

Meta把语音识别、说话人分离和端点检测三个模型合成了一个，延迟更低，故障点更少。

3 sources73° AI heatLast updated 2026/9/2 05:37:12

Evidence

3 sources

Primary sourcemarktechpost

2026/9/2 05:37:12View source

Related source 1IT之家

2026/9/2 00:23:26View source

Related source 2Meta AI

2026/9/1 17:26:10View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story