Skip to main content
Emitted when the service detects user speech on the input audio stream. This can arrive before any transcription text is available.

​
Event fields

​
string
required
Unique id for this server event.
​
string
required
Event type. Must be input_audio.speech_started.
​
string
required
Provisional user audio item id used to correlate later transcription events and the created conversation item.
​
integer
required
Speech start time in milliseconds on the session input-audio timeline.