Meta Releases Muse Voice: Real-Time Audio Transcription for 70+ Languages
alexandr_wang · x · 2026-09-02
Meta has introduced Muse Voice Transcribe, its first real-time audio perception model. It supports real-time transcription in over 70 languages and features diarization capable of distinguishing between more than 20 speakers. The feature is now available in the Meta AI macOS app.
More from Multimodal
- DLSS 5 comes to ComfyUI: Incredible in-game results in Diablo 4 — Choidonhyeon · 2026-09-02
- Fable Studio 5.1 generates house tour via code from a lot image — jongranskog · 2026-09-02
- Open source approach aligns with World Labs' Atlas release — mickmumpitz · 2026-09-02
- Comparing leading video generation models with identical prompts — madeofAjala · 2026-09-02
- Sol 5.6 writes code from an image screenshot — CondomHogWasher · 2026-09-02
- Synthesia Exec Discusses AI Video Tech and Deepfake Prevention — alexvoica · 2026-09-02