class

OpenAI::RealtimeResponse

Inherits JSON::Serializable < Reference < Object

The response resource.

Constructors

new(pull : JSON::PullParser)

new(id : String | Nil = nil, object : Hash(String, JSON::Any) | Nil = nil, status : RealtimeResponseStatus | Nil = nil, status_details : RealtimeResponseStatusDetails | Nil = nil, output : Array(RealtimeConversationItem) | Nil = nil, metadata : Metadata | Nil = nil, audio : RealtimeResponseAudio | Nil = nil, usage : RealtimeResponseUsage | Nil = nil, conversation_id : String | Nil = nil, output_modalities : Array(RealtimeResponseOutputModalitiesItem) | Nil = nil, max_output_tokens : RealtimeResponseMaxOutputTokens | Nil = nil)

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Instance methods

audio

Configuration for audio output.

audio=(audio : RealtimeResponseAudio | Nil)

Configuration for audio output.

conversation_id

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 automatically by VAD the response will be added to the default conversation

conversation_id=(conversation_id : String | Nil)

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 automatically by VAD the response will be added to the default conversation

id

The unique ID of the response, will look like resp_1234.

id=(id : String | Nil)

The unique ID of the response, will look like resp_1234.

max_output_tokens

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

max_output_tokens=(max_output_tokens : RealtimeResponseMaxOutputTokens | Nil)

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

metadata

metadata=(metadata : Metadata | Nil)

object

The object type, must be realtime.response.

object=(object : Hash(String, JSON::Any) | Nil)

The object type, must be realtime.response.

output

The list of output items generated by the response.

output=(output : Array(RealtimeConversationItem) | Nil)

The list of output items generated by the response.

output_modalities

The set of modalities the model used to respond, currently the only possible values are [\"audio\"], [\"text\"]. Audio output always include a text transcript. Setting the output to mode text will disable audio output from the model.

output_modalities=(output_modalities : Array(RealtimeResponseOutputModalitiesItem) | Nil)

The set of modalities the model used to respond, currently the only possible values are [\"audio\"], [\"text\"]. Audio output always include a text transcript. Setting the output to mode text will disable audio output from the model.

status

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

status=(status : RealtimeResponseStatus | Nil)

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

status_details

Additional details about the status.

status_details=(status_details : RealtimeResponseStatusDetails | Nil)

Additional details about the status.

usage

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.

usage=(usage : RealtimeResponseUsage | Nil)

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.