Event ·Multi-source

Meta发布实时音频感知模型Muse Voice Transcribe

Meta推出首个实时音频感知模型Muse Voice Transcribe，支持20余人分轨转写。该模型通过Meta Model API调用，定价为每1000分钟音频3美元。模型整合流式自动语音识别、说话人分离与端点检测，支持70余种语言，其中25种已完成验证。截至2026年9月1日，该模型位列Artificial Analysis流式语音转文本排行榜第1名。

Current read

Meta发布实时音频转写模型，20人分轨只需3美元/千分钟，还能自适应调整延迟。

3 sources73° AI heatLast updated 2026/9/2 00:23:26

Evidence

3 sources

Primary sourceIT之家

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

Related source 1Meta AI

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

Related source 2marktechpost

2026/9/2 05:37:12View 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