Struct RealtimeSession

pub struct RealtimeSession {

    pub id: Option<String>,
    pub modalities: Option<Vec<RealtimeSessionModality>>,
    pub model: Option<RealtimeSessionModel>,
    pub instructions: Option<String>,
    pub voice: Option<VoiceIdsShared>,
    pub input_audio_format: Option<RealtimeSessionInputAudioFormat>,
    pub output_audio_format: Option<RealtimeSessionOutputAudioFormat>,
    pub input_audio_transcription: Option<RealtimeSessionInputAudioTranscription>,
    pub turn_detection: Option<RealtimeSessionTurnDetection>,
    pub input_audio_noise_reduction: Option<RealtimeSessionInputAudioNoiseReduction>,
    pub speed: Option<f64>,
    pub tracing: Option<RealtimeSessionTracing>,
    pub tools: Option<Vec<RealtimeSessionTool>>,
    pub tool_choice: Option<String>,
    pub temperature: Option<f64>,
    pub max_response_output_tokens: Option<RealtimeSessionMaxResponseOutputTokens>,
}

Realtime session object configuration.

Fields

id: Option<String>

Unique identifier for the session that looks like sess_1234567890abcdef.

modalities: Option<Vec<RealtimeSessionModality>>

The set of modalities the model can respond with. To disable audio, set this to [“text”].

model: Option<RealtimeSessionModel>

The Realtime model used for this session.

instructions: Option<String>

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. “be extremely succinct”, “act friendly”, “here are examples of good responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion into your voice”, “laugh frequently”). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

voice: Option<VoiceIdsShared>

The voice the model uses to respond. Voice cannot be changed during the session once the model has responded with audio at least once. Current voice options are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, and verse.

input_audio_format: Option<RealtimeSessionInputAudioFormat>

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

output_audio_format: Option<RealtimeSessionOutputAudioFormat>

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, output audio is sampled at a rate of 24kHz.

input_audio_transcription: Option<RealtimeSessionInputAudioTranscription>

Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through the /audio/transcriptions endpoint and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

turn_detection: Option<RealtimeSessionTurnDetection>

Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. Semantic VAD is more advanced and uses a turn detection model (in conjuction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with “uhhm”, the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

input_audio_noise_reduction: Option<RealtimeSessionInputAudioNoiseReduction>

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

speed: Option<f64>

The speed of the model’s spoken response. 1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed. This value can only be changed in between model turns, not while a response is in progress.

tracing: Option<RealtimeSessionTracing>

Configuration options for tracing. Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified.

auto will create a trace for the session with default values for the workflow name, group id, and metadata.

tools: Option<Vec<RealtimeSessionTool>>

Tools (functions) available to the model.

tool_choice: Option<String>

How the model chooses tools. Options are auto, none, required, or specify a function.

temperature: Option<f64>

Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance.

max_response_output_tokens: Option<RealtimeSessionMaxResponseOutputTokens>

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.

Implementations

impl RealtimeSession

pub fn builder() -> RealtimeSessionBuilder<((), (), (), (), (), (), (), (), (), (), (), (), (), (), (), ())>

Create a builder for building RealtimeSession. On the builder, call .id(...)(optional), .modalities(...)(optional), .model(...)(optional), .instructions(...)(optional), .voice(...)(optional), .input_audio_format(...)(optional), .output_audio_format(...)(optional), .input_audio_transcription(...)(optional), .turn_detection(...)(optional), .input_audio_noise_reduction(...)(optional), .speed(...)(optional), .tracing(...)(optional), .tools(...)(optional), .tool_choice(...)(optional), .temperature(...)(optional), .max_response_output_tokens(...)(optional) to set the values of the fields. Finally, call .build() to create the instance of RealtimeSession.

Trait Implementations

impl Clone for RealtimeSession

fn clone(&self) -> RealtimeSession

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for RealtimeSession

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for RealtimeSession

fn default() -> RealtimeSession

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for RealtimeSession

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for RealtimeSession

fn eq(&self, other: &RealtimeSession) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for RealtimeSession

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for RealtimeSession