`pascal-transcribe-live`

Live speech-to-text. WebSocket only. $0.22 per audio hour, or $0.25 per audio hour with speaker diarization, plus the $0.05 request fee.

Native stream: PCM16 mono on wss://api.pascalai.co/v1/speech-to-text/realtime. Default 16000 Hz.. Live price and availability are on GET /v1/models/pascal-transcribe-live.

Open wss://api.pascalai.co/v1/speech-to-text/realtime?model=pascal-transcribe-live.
Wait for session.created. Send one session.update, then binary PCM16 mono at session.sample_rate. Omit sample_rate and the rate is 16000. If the bytes are a different rate, the transcript can come out degraded. session.update is accepted only before the first audio frame.
session.close ends the audio and closes the socket. That is the stop.
session.commit also finishes the audio and leaves the socket open until session.close. session.clear and session.cancel are accepted and do not change the stream.
Each finished turn arrives as transcript.completed. This model does not send transcript.delta.
When speaker_diarization is true, transcript.completed includes speaker. When timestamp_granularity is segment, it includes start and end, in seconds.
The event does not include language, duration, or an utterance id.
The field name is speaker_diarization. diarize is rejected. emotion, accent, deepfake, and PII fields are rejected.
A session pays $0.05, then connected time at $0.22 per hour, or $0.25 per hour when speaker diarization is on. A session runs for up to 5 hours.
Hosted model. The studio signup credit can spend it.
A browser sends the API key as api_key on the query string.

Parameters

Field	Type	Description
`session.sample_rate` Default 16000	integer	8000, 11025, 16000, 22050, 32000, 44100, or 48000. Omit it and the rate is 16000 Hz. The bytes have to already be that rate. A live frame has no header, so a mismatch is still accepted and the transcript can come out degraded.
`session.language` Default auto	string	auto detects the language. An ISO 639-1 code selects it. ['af', 'am', 'ar', 'as', 'az', 'ba', 'be', 'bg', 'bn', 'bo', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el', 'en', 'es', 'et', 'eu', 'fa', 'fi', 'fo', 'fr', 'gl', 'gu', 'ha', 'haw', 'he', 'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'is', 'it', 'ja', 'jw', 'ka', 'kk', 'km', 'kn', 'ko', 'la', 'lb', 'ln', 'lo', 'lt', 'lv', 'mg', 'mi', 'mk', 'ml', 'mn', 'mr', 'ms', 'mt', 'my', 'ne', 'nl', 'nn', 'no', 'oc', 'pa', 'pl', 'ps', 'pt', 'ro', 'ru', 'sa', 'sd', 'si', 'sk', 'sl', 'sn', 'so', 'sq', 'sr', 'su', 'sv', 'sw', 'ta', 'te', 'tg', 'th', 'tk', 'tl', 'tr', 'tt', 'uk', 'ur', 'uz', 'vi', 'yi', 'yo', 'yue', 'zh']
`session.speaker_diarization` Default false	boolean	Label each turn with a speaker number. When true, connected time is billed at $0.25 per hour.
`session.custom_terms`	string or array	Names and jargon to bias the transcript. A comma-separated string or a list of strings. At most 1000 terms and 8000 characters.
`session.timestamp_granularity` Default none	string	none returns transcript only. segment also sends start and end, in seconds, on each transcript.completed.

Example

const socket = new WebSocket(
  'wss://api.pascalai.co/v1/speech-to-text/realtime?model=pascal-transcribe-live&api_key=' + key
);
socket.binaryType = 'arraybuffer';
socket.onopen = () => {
  socket.send(JSON.stringify({
    type: 'session.update',
    session: {
      language: 'auto',
      speaker_diarization: false,
      timestamp_granularity: 'none',
    },
  }));
};
// binary Int16 PCM16 mono frames at session.sample_rate (default 16000)
socket.send(JSON.stringify({ type: 'session.close' }));