跳到正文
AI at Meta· @AIatMeta · X·· 2026-09-02精选AI 评分72
AI 导读

Meta Superintelligence Labs 发布首个实时音频感知模型 Muse Voice Transcribe,支持实时流式 ASR、20 人以上说话人分离和端点检测。该模型支持多语言并无缝切换语种,可通过语言、关键词和上下文偏置提升准确率,在 Artificial Analysis 流式语音转文字和公开说话人分离基准上排名第一。

推荐理由

Meta 公布实时语音感知模型的能力清单与榜单排名,可据此判断流式 ASR 的当前水平。

正文 · 原文

Introducing Muse Voice Transcribe, the first real-time audio perception model from Meta Superintelligence Labs.

Muse Voice Transcribe delivers real-time streaming ASR, diarization with 20+ speakers, and endpointing. It’s multilingual with seamless code-switching and improves accuracy with language, keyword, and context biasing.

The model ranks first on @ArtificialAnlys streaming speech-to-text and on public diarization benchmarks.

来源:AI at Meta · x.com