session.update
开发中Send this event to update the session’s default configuration.
请求参数
Optional client-generated ID used to identify this event.
The event type, must be "session.update".
object类型，以下参数为其中参数。Session configuration to update.
The set of modalities the model can respond with. To disable audio, set this to ["text"].
The default system instructions prepended to model calls.
The voice the model uses to respond - one of alloy, echo, or shimmer. Cannot be changed once the model has responded with audio at least once.
The format of input audio. Options are "pcm16", "g711_ulaw", or "g711_alaw".
The format of output audio. Options are "pcm16", "g711_ulaw", or "g711_alaw".
object类型，以下model为其中参数。
The model to use for transcription (e.g., "whisper-1").
object类型，以下type、threshold、prefix_padding_ms、silence_duration_ms为其中参数。
为type,Type of turn detection, only "server_vad" is currently supported.
Activation threshold for VAD (0.0 to 1.0).
Amount of audio to include before speech starts (in milliseconds).
Duration of silence to detect speech stop (in milliseconds).
Tools (functions) available to the model.
How the model chooses tools. Options are "auto", "none", "required", or specify a function.
Sampling temperature for the model.
Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or "inf" for the maximum available tokens for a given model. Defaults to "inf".