- TranscriptEvent
- SessionMetadata
- ErrorEvent
An event emitted when a chunk of the audio stream has been transcribed.
speakerstringrequired
Whether a line of the transcript was spoken by the user or the non-user party.
Format:
TranscriptSpeaker (string)
Possible values: [USER
, SUBJECT
]
Example:
USER
transcriptstringrequired
The transcript line corresponding to a section of the audio stream.
Example:
hello good afternoon
typestringrequired
Type discriminator.
Default value:
transcript
Example:
transcript
The event emitted when the session has been established, as a response to the initial metadata frame sent by the client.
sessionIdstringrequired
The unique identifier of the session.
typestringrequired
Type discriminator.
Default value:
sessionMetadata
Example:
sessionMetadata
An event emitted when an error has occurred.
messagestringrequired
The error message.
typestringrequired
Type discriminator.
Default value:
error
Example:
error
TranscribeAudioEvent
{
"speaker": "USER",
"transcript": "hello good afternoon",
"type": "transcript"
}