Interface SessionCreateResponse

A new Realtime session configuration, with an ephermeral key. Default TTL for keys is one minute.

interface SessionCreateResponse {
    client_secret: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.ClientSecret;
    input_audio_format?: string;
    input_audio_transcription?: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.InputAudioTranscription;
    instructions?: string;
    max_response_output_tokens?: number | "inf";
    modalities?: ("text" | "audio")[];
    output_audio_format?: string;
    speed?: number;
    temperature?: number;
    tool_choice?: string;
    tools?: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.Tool[];
    tracing?: "auto" | OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.TracingConfiguration;
    turn_detection?: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.TurnDetection;
    voice?:
        | string & {}
        | "alloy"
        | "ash"
        | "ballad"
        | "coral"
        | "echo"
        | "sage"
        | "shimmer"
        | "verse";
}

Properties

client_secret input_audio_format? input_audio_transcription? instructions? max_response_output_tokens? modalities? output_audio_format? speed? temperature? tool_choice? tools? tracing? turn_detection? voice?

Properties

client_secret

client_secret: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.ClientSecret

Ephemeral key returned by the API.

Optionalinput_audio_format

input_audio_format?: string

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

Optionalinput_audio_transcription

input_audio_transcription?: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.InputAudioTranscription

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 and should be treated as rough guidance rather than the representation understood by the model.

Optionalinstructions

instructions?: 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.

Optionalmax_response_output_tokens

max_response_output_tokens?: number | "inf"

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.

Optionalmodalities

modalities?: ("text" | "audio")[]

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

Optionaloutput_audio_format

output_audio_format?: string

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.

Optionalspeed

speed?: number

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.

Optionaltemperature

temperature?: number

Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.

Optionaltool_choice

tool_choice?: string

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

Optionaltools

tools?: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.Tool[]

Tools (functions) available to the model.

Optionaltracing

tracing?: "auto" | OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.TracingConfiguration

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.

Optionalturn_detection

turn_detection?: OpenAIClient.Beta.Realtime.Sessions.SessionCreateResponse.TurnDetection

Configuration for turn detection. Can be set to null to turn off. 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.

Optionalvoice

voice?:
    | string & {}
    | "alloy"
    | "ash"
    | "ballad"
    | "coral"
    | "echo"
    | "sage"
    | "shimmer"
    | "verse"

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, sage, shimmer, and verse.

Settings

Member Visibility

On This Page

Properties