# Muse Voice Transcribe 1.0

> Meta's Muse Voice Transcribe speech-to-text over the Meta developer API - 25 languages with code-switching (Korean included), speaker diarization, endpointing, keyword and language biasing. Billed per second of audio (0.11625 credits/s, about 7 credits per minute), up to 10 minutes per request.

- **Provider**: meta-asr
- **Model ID**: meta/muse-voice-transcribe-1.0
- **Category**: speech_to_text
- **Credits**: 70 per request
- **Pricing Type**: formula

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `mode` (string, optional): PUSH_TO_TALK returns one transcript; ENDPOINTING splits into turns at speech boundaries; DIARIZATION additionally labels speakers. (Default: `PUSH_TO_TALK`; Options: `PUSH_TO_TALK`, `ENDPOINTING`, `DIARIZATION`)
- `audio` (string, **required**): Audio file URL (mp3, m4a, wav, ogg, webm, mp4 audio track). Normalized to mono 16-bit PCM WAV at 24 kHz before upload. Max 10 minutes per request.
- `keywords` (array, optional): Names, acronyms or product terms to bias recognition toward.
- `language_bias` (array, optional): Language hint (steers recognition, does not force it). Omit for automatic detection across all 25 languages.

## Example Request

```json
{
  "model": "meta/muse-voice-transcribe-1.0",
  "input": {
    "mode": "PUSH_TO_TALK",
    "language_bias": [
      "English"
    ],
    "audio": "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

meta, muse, speech-to-text, transcription, diarization, multilingual

## Documentation

https://dev.meta.ai/docs/speech-to-text