Billing note Credits are reserved in 5-minute (300s) blocks as the session runs and settled on the seconds Meta actually reports processing - not on connection time. If the gateway is redeployed mid-session, your connection is closed and any partial block is settled and refunded, not lost.

MetaFastHigh

Muse Voice Transcribe 1.0 (Realtime)

Meta's Muse Voice Transcribe over a WebSocket - stream 16-bit PCM (24 kHz or 16 kHz mono) and receive partial and final transcripts while you speak, with endpointing and diarization. Billed per second of audio Meta processed (0.11625 credits/s, 35 credits per 5-minute block), sessions up to 20 minutes.

35 credits

per 5-minute block (0.11625 credits/s)

Streaming partial and final transcripts while the caller is still speaking

25 languages with code-switching, Korean included

Speaker diarization and endpointing in DIARIZATION/ENDPOINTING modes

Keyword and language biasing, same as the file transcription endpoint

Sessions up to 20 minutes; settlement follows Meta's measured audio, not wall-clock time

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "meta/muse-voice-transcribe-1.0/realtime",
  "input": {
    "model": "meta/muse-voice-transcribe-1.0/realtime",
    "audioEncoding": "PCM_24KHZ",
    "mode": "ENDPOINTING",
    "partialMode": "CUMULATIVE",
    "emitAudioProgress": false,
    "keywords": [
      "Core.Today"
    ],
    "languageBias": [
      "Korean"
    ],
    "customerId": "member-123"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`audioEncoding`	string	No	PCM_24KHZ	Raw PCM 16-bit mono sample rate of the binary frames you send. PCM_24KHZPCM_16KHZ
`mode`	string	No	PUSH_TO_TALK	PUSH_TO_TALK returns one running transcript; ENDPOINTING splits into turns at speech boundaries; DIARIZATION additionally labels speakers. PUSH_TO_TALKENDPOINTINGDIARIZATION
`partialMode`	string	No	CUMULATIVE	CUMULATIVE partials replace the previous one; DELTA sends only new text. CUMULATIVEDELTA
`emitAudioProgress`	boolean	No	false	Forward Meta's ~80ms audioProgress events (audioProcessedMs) to your client.
`keywords`	array	No	-	Names, acronyms or product terms to bias recognition toward.
`language_bias`	array	No	-	Language hint (steers recognition, does not force it). Omit for automatic detection across all 25 languages. ArabicBengaliDutchEnglishFrenchGermanHebrewHindiIndonesianItalianJapaneseKannadaKoreanMalayMandarin ChineseMarathiPolishPortugueseSpanishTagalogTamilTeluguThaiTurkishVietnamese

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Handshake frame

The first text frame you send after the WebSocket connects, in ENDPOINTING mode with a Korean language hint. Never put a real API key in client-side/browser code - use a server-side connection instead.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "meta/muse-voice-transcribe-1.0/realtime",
  "input": {
    "model": "meta/muse-voice-transcribe-1.0/realtime",
    "audioEncoding": "PCM_24KHZ",
    "mode": "ENDPOINTING",
    "partialMode": "CUMULATIVE",
    "emitAudioProgress": false,
    "keywords": [
      "Core.Today"
    ],
    "languageBias": [
      "Korean"
    ],
    "customerId": "member-123"
  }
}'