API access

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

muse-voice-transcribe-1.0

API price

$3.00 / 1,000 audio minutes

Equivalent

$0.18 / audio hour
Access paths

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.

Meta Model API

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 docs
Meta AI for Mac

Meta says Mac dictation is powered by Muse Voice Transcribe. Treat this as a product access path, not endpoint or billing documentation.

View Meta AI
Muse Code

Meta also lists Muse Code as an access path for voice input. Use current Muse Code materials for workflow details.

View Muse Code
Documented capabilities

Capabilities to verify before integration

Streaming transcription

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.

Speaker diarization

The launch documentation describes native diarization for conversations with 20+ speakers, including long audio examples beyond one hour.

Endpointing

Endpointing is documented as part of the same model family, marking when speech begins and when a turn has finished.

Language and context biasing

The model supports multilingual speech, code-switching, and language, keyword, and context biasing for terms such as names, products, and places.

Streaming workflow

Integration checklist without guessed endpoints

1

Request audio permission and confirm you are allowed to record the captured audio.

2

Choose an officially supported live-stream or file-transcription mode without assuming identical retry, silence, or billing behavior.

3

Handle transcript text, speaker labels, and endpoint signals as model output, with human review for sensitive uses.

4

Before launch, confirm account access, region, rate limits, data retention, and production terms in Meta's console.

Integration boundaries

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.

Read the launch notes