Interface RealtimeResponse

The response resource.

interface RealtimeResponse {
    conversation_id?: string;
    id?: string;
    max_output_tokens?: number | "inf";
    metadata?: null | Metadata;
    modalities?: ("text" | "audio")[];
    object?: "realtime.response";
    output?: ConversationItem[];
    output_audio_format?: "pcm16" | "g711_ulaw" | "g711_alaw";
    status?:
        | "in_progress"
        | "completed"
        | "failed"
        | "incomplete"
        | "cancelled";
    status_details?: RealtimeResponseStatus;
    temperature?: number;
    usage?: RealtimeResponseUsage;
    voice?:
        | string & {}
        | "alloy"
        | "ash"
        | "ballad"
        | "coral"
        | "echo"
        | "sage"
        | "shimmer"
        | "verse";
}

Properties

conversation_id? id? max_output_tokens? metadata? modalities? object? output? output_audio_format? status? status_details? temperature? usage? voice?

Properties

Optionalconversation_id

conversation_id?: string

Which conversation the response is added to, determined by the conversation field in the response.create event. If auto, the response will be added to the default conversation and the value of conversation_id will be an id like conv_1234. If none, the response will not be added to any conversation and the value of conversation_id will be null. If responses are being triggered by server VAD, the response will be added to the default conversation, thus the conversation_id will be an id like conv_1234.

Optionalid

id?: string

The unique ID of the response.

Optionalmax_output_tokens

max_output_tokens?: number | "inf"

Maximum number of output tokens for a single assistant response, inclusive of tool calls, that was used in this response.

Optionalmetadata

metadata?: null | Metadata

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Optionalmodalities

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

The set of modalities the model used to respond. If there are multiple modalities, the model will pick one, for example if modalities is ["text", "audio"], the model could be responding in either text or audio.

Optionalobject

object?: "realtime.response"

The object type, must be realtime.response.

Optionaloutput

output?: ConversationItem[]

The list of output items generated by the response.

Optionaloutput_audio_format

output_audio_format?: "pcm16" | "g711_ulaw" | "g711_alaw"

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

Optionalstatus

status?:
    | "in_progress"
    | "completed"
    | "failed"
    | "incomplete"
    | "cancelled"

The final status of the response (completed, cancelled, failed, or incomplete, in_progress).

Optionalstatus_details

status_details?: RealtimeResponseStatus

Additional details about the status.

Optionaltemperature

temperature?: number

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

Optionalusage

usage?: RealtimeResponseUsage

Usage statistics for the Response, this will correspond to billing. A Realtime API session will maintain a conversation context and append new Items to the Conversation, thus output from previous turns (text and audio tokens) will become the input for later turns.

Optionalvoice

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

The voice the model used to respond. Current voice options are alloy, ash, ballad, coral, echo, sage, shimmer, and verse.

Settings

Member Visibility

On This Page

Properties