class

OpenAI::RealtimeSessionCreateResponseGA

Inherits JSON::Serializable < Reference < Object

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

Constructors

new(pull : JSON::PullParser)

new(client_secret : RealtimeSessionCreateResponseGAClientSecret = RealtimeSessionCreateResponseGAClientSecret.new, type_value : RealtimeSessionCreateResponseGAType = RealtimeSessionCreateResponseGAType::Realtime, output_modalities : Array(RealtimeSessionCreateResponseGAOutputModalitiesItem) | Nil = nil, model : RealtimeSessionCreateResponseGAModel | Nil = nil, instructions : String | Nil = nil, audio : RealtimeSessionCreateResponseGAAudio | Nil = nil, include_value : Array(RealtimeSessionCreateResponseGAIncludeItem) | Nil = nil, tracing : RealtimeSessionCreateResponseGATracing | Nil = nil, tools : Array(RealtimeSessionCreateResponseGAToolsItem) | Nil = nil, tool_choice : RealtimeSessionCreateResponseGAToolChoice | Nil = nil, max_output_tokens : RealtimeSessionCreateResponseGAMaxOutputTokens | Nil = nil, truncation : RealtimeTruncation | Nil = nil, prompt : Prompt | Nil = nil)

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

Instance methods

audio

Configuration for input and output audio.

audio=(audio : RealtimeSessionCreateResponseGAAudio | Nil)

Configuration for input and output audio.

client_secret

Ephemeral key returned by the API.

client_secret=(client_secret : RealtimeSessionCreateResponseGAClientSecret)

Ephemeral key returned by the API.

include_value

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

include_value=(include_value : Array(RealtimeSessionCreateResponseGAIncludeItem) | Nil)

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

instructions

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.

instructions=(instructions : String | Nil)

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.

max_output_tokens

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.

max_output_tokens=(max_output_tokens : RealtimeSessionCreateResponseGAMaxOutputTokens | Nil)

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.

model

The Realtime model used for this session.

model=(model : RealtimeSessionCreateResponseGAModel | Nil)

The Realtime model used for this session.

output_modalities

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

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

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

prompt

prompt=(prompt : Prompt | Nil)

tool_choice

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

tool_choice=(tool_choice : RealtimeSessionCreateResponseGAToolChoice | Nil)

How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.

tools

Tools available to the model.

tools=(tools : Array(RealtimeSessionCreateResponseGAToolsItem) | Nil)

Tools available to the model.

tracing

tracing=(tracing : RealtimeSessionCreateResponseGATracing | Nil)

truncation

truncation=(truncation : RealtimeTruncation | Nil)

type_value

The type of session to create. Always realtime for the Realtime API.

type_value=(type_value : RealtimeSessionCreateResponseGAType)

The type of session to create. Always realtime for the Realtime API.