Muse Voice Transcribe API Guide
For developers evaluating Meta Model API: verified model name, pricing, real-time capabilities, and privacy boundaries without inventing endpoints, auth fields, or response schemas.
Last verified: September 2, 2026
Model
API price
Equivalent
Separate API, Mac, and Muse Code access
All three paths appear in Meta's public materials, but Meta Model API is the developer integration path that should be evaluated from API documentation.
Developer evaluation and production integration should start with Meta Model API speech-to-text docs. The documented model name is muse-voice-transcribe-1.0.
Open docsMeta says Mac dictation is powered by Muse Voice Transcribe. Treat this as a product access path, not endpoint or billing documentation.
View Meta AIMeta also lists Muse Code as an access path for voice input. Use current Muse Code materials for workflow details.
View Muse CodeCapabilities to verify before integration
Meta describes Muse Voice Transcribe as a real-time audio perception model for streaming ASR, so text can be produced while speech is still arriving.
The launch documentation describes native diarization for conversations with 20+ speakers, including long audio examples beyond one hour.
Endpointing is documented as part of the same model family, marking when speech begins and when a turn has finished.
The model supports multilingual speech, code-switching, and language, keyword, and context biasing for terms such as names, products, and places.
Integration checklist without guessed endpoints
Request audio permission and confirm you are allowed to record the captured audio.
Choose an officially supported live-stream or file-transcription mode without assuming identical retry, silence, or billing behavior.
Handle transcript text, speaker labels, and endpoint signals as model output, with human review for sensitive uses.
Before launch, confirm account access, region, rate limits, data retention, and production terms in Meta's console.
What still belongs in official docs
Authentication
Assume authentication is account-scoped through Meta Model API until the official docs for your account state the exact token, header, and project setup. This guide intentionally avoids placeholder keys.
Endpoint and schema
This site does not publish guessed request paths, authentication headers, WebSocket formats, or response JSON. Use the current Meta Model API docs and cookbook for implementation details.
ZDR and data handling
Zero data retention, storage, regional processing, and enterprise controls should be confirmed in Meta's current API terms before sending production audio.
Cookbook examples
Treat official cookbook examples as the starting point for streaming behavior, file transcription behavior, error handling, and production retries.