transcript message

A partial (receive_partial_transcripts) or final (receive_final_transcripts) transcript.

Delivery

On the WebSocket with messages_config.receive_partial_transcripts or messages_config.receive_final_transcripts; to your callback as live.transcript with callback_config.receive_final_transcripts.

Fields

session_id string required

Identifier of the session.
created_at string required

When the message was sent (ISO 8601, UTC).
type "transcript" required
data object required
3 fields
- id string required
  
  Identifier of the utterance: <channel>_<index>, stable for the whole session.
- is_final boolean required
  
  false: a partial transcript, replaced by the next one; true: the final transcript of the utterance.
- utterance object required
  
  A piece of speech between two pauses, on one channel.
  11 fields
  - text string required
    
    The transcript. With named entity recognition or PII redaction on, it carries their inline elements (<ner:name id="1">…</ner:name>, <pii:email id="1"/>).
  - start number required
    
    Start, in seconds from the start of the audio.
  - end number required
    
    End, in seconds from the start of the audio.
  - language string required
    
    Language spoken (ISO 639-1).
  - confidence number required
    
    Confidence, from 0 to 1.
  - channel integer required
    
    Audio channel the utterance was heard on, from 0.
  - speaker integer
    
    Speaker number, with diarization.
    
    default: null
  - words array of object required
    
    The words with their timestamps.
    
    5 fields
    
    word string required
    
    The word, with its leading space when it follows another.
    
    start number required
    
    Start of the word, in seconds from the start of the audio.
    
    end number required
    
    End of the word, in seconds from the start of the audio.
    
    confidence number required
    
    Confidence, from 0 to 1.
    
    speaker integer
    
    Speaker of the word, with diarization.
    
    default: null
  - text_raw string
    
    The transcript without inline elements (with named entity recognition; never with PII redaction).
    
    default: null
  - entities array of object
    
    The entities of the utterance, with named entity recognition or PII redaction.
    
    default: null
    
    7 fields
    
    label string
    
    Entity type, for example name, phone_number, location_city.
    
    default: null
    
    id integer
    
    The entity's number in the session, per type: the same person is always the same number.
    
    default: null
    
    action string
    
    ner: tagged; otherwise how the personal data was redacted.
    
    default: null
    
    score number
    
    Confidence, from 0 to 1.
    
    default: null
    
    text string
    
    The entity as heard (never sent for masked personal data unless pii.return_entities).
    
    default: null
    
    start integer
    
    Offset of the entity's element in text, in characters.
    
    default: null
    
    end integer
    
    End offset of the entity's element in text, in characters.
    
    default: null
  - forced "max_duration"
    
    Set when the utterance was closed by maximum_duration_without_endpointing rather than by a pause.
    
    default: null

Example

{
  "session_id": "string",
  "created_at": "string",
  "type": "transcript",
  "data": {
    "id": "00_00000003",
    "is_final": false,
    "utterance": {
      "text": "Hello, how can I help you?",
      "start": 0.5,
      "end": 0.5,
      "language": "en",
      "confidence": 0.5,
      "channel": 0,
      "speaker": 0,
      "words": [
        {
          "word": " hello",
          "start": 0.5,
          "end": 0.5,
          "confidence": 0.5,
          "speaker": 0
        }
      ],
      "text_raw": "string",
      "entities": [
        {
          "label": "string",
          "id": 0,
          "action": "string",
          "score": 0.5,
          "text": "string",
          "start": 0,
          "end": 0
        }
      ],
      "forced": "max_duration"
    }
  }
}