Session configuration to update.
| Name | Type | Description | Notes |
|---|---|---|---|
| modalities | List<String> | The set of modalities the model can respond with. To disable audio, set this to ["text"]. | [optional] |
| instructions | String | The default system instructions prepended to model calls. | [optional] |
| voice | String | 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. | [optional] |
| inputAudioFormat | String | The format of input audio. Options are "pcm16", "g711_ulaw", or "g711_alaw". | [optional] |
| outputAudioFormat | String | The format of output audio. Options are "pcm16", "g711_ulaw", or "g711_alaw". | [optional] |
| inputAudioTranscription | RealtimeClientEventSessionUpdateSessionInputAudioTranscription | [optional] | |
| turnDetection | RealtimeClientEventSessionUpdateSessionTurnDetection | [optional] | |
| tools | List<RealtimeClientEventSessionUpdateSessionToolsInner> | Tools (functions) available to the model. | [optional] |
| toolChoice | String | How the model chooses tools. Options are "auto", "none", "required", or specify a function. | [optional] |
| temperature | BigDecimal | Sampling temperature for the model. | [optional] |
| maxOutputTokens | RealtimeClientEventResponseCreateResponseMaxOutputTokens | [optional] |