Speech to text

Muse Voice Transcribe is Meta's speech-to-text model on Meta Model API. Transcribe live audio or an existing recording, with speech-turn detection, speaker labels, and vocabulary biasing.

Available endpoints

Both endpoints run the same model.

EndpointUse it forHow you connect
wss://api.meta.ai/v1/asr/realtimeLive audio: voice agents, dictation, captionsWebSocket. Authenticate in the handshake frame; the Authorization header is ignored.
POST https://api.meta.ai/v1/asr/transcribeA recording you already haveMultipart upload. Authenticate with the Authorization header.

See the Voice API reference for full request and response schemas.

Features

FeatureWhat you get