RealtimeServerEventInputAudioBufferSpeechStopped
objectReturned in server_vad mode when the server detects the end of speech in
the audio buffer. The server will also send an conversation.item.created
event with the user message item that is created from the audio buffer.
The unique ID of the server event.
The event type, must be input_audio_buffer.speech_stopped.
Allowed values:input_audio_buffer.speech_stopped
Milliseconds since the session started when speech stopped. This will
correspond to the end of audio sent to the model, and thus includes the
min_silence_duration_ms configured in the Session.
The ID of the user message item that will be created.
RealtimeServerEventRateLimitsUpdated
objectEmitted at the beginning of a Response to indicate the updated rate limits.
When a Response is created some tokens will be “reserved” for the output
tokens, the rate limits shown here reflect that reservation, which is then
adjusted accordingly once the Response is completed.
The unique ID of the server event.
The event type, must be rate_limits.updated.
Allowed values:rate_limits.updated
List of rate limit information.
Show Child Parameters
RealtimeServerEventResponseAudioDelta
objectReturned when the model-generated audio is updated.
The unique ID of the server event.
The event type, must be response.audio.delta.
Allowed values:response.audio.delta
The ID of the response.
The ID of the item.
The index of the output item in the response.
The index of the content part in the item’s content array.
Base64-encoded audio data delta.
RealtimeServerEventResponseAudioDone
objectReturned when the model-generated audio is done. Also emitted when a Response
is interrupted, incomplete, or cancelled.
The unique ID of the server event.
The event type, must be response.audio.done.
Allowed values:response.audio.done
The ID of the response.
The ID of the item.
The index of the output item in the response.
The index of the content part in the item’s content array.
RealtimeServerEventResponseAudioTranscriptDelta
objectReturned when the model-generated transcription of audio output is updated.
The unique ID of the server event.
The event type, must be response.audio_transcript.delta.
Allowed values:response.audio_transcript.delta
The ID of the response.
The ID of the item.
The index of the output item in the response.
The index of the content part in the item’s content array.
The transcript delta.