class

OpenAI::RealtimeSessionCreateRequest

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)
Source
new(client_secret : RealtimeSessionCreateRequestClientSecret = RealtimeSessionCreateRequestClientSecret.new, modalities : Hash(String, JSON::Any) | Nil = nil, instructions : String | Nil = nil, voice : VoiceIdsShared | Nil = nil, input_audio_format : String | Nil = nil, output_audio_format : String | Nil = nil, input_audio_transcription : RealtimeSessionCreateRequestInputAudioTranscription | Nil = nil, speed : Float64 | Nil = nil, tracing : RealtimeSessionCreateRequestTracing | Nil = nil, turn_detection : RealtimeSessionCreateRequestTurnDetection | Nil = nil, tools : Array(RealtimeSessionCreateRequestToolsItem) | Nil = nil, tool_choice : String | Nil = nil, temperature : Float64 | Nil = nil, max_response_output_tokens : RealtimeSessionCreateRequestMaxResponseOutputTokens | Nil = nil, truncation : RealtimeTruncation | Nil = nil, prompt : Prompt | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

client_secret

Ephemeral key returned by the API.

Source
client_secret=(client_secret : RealtimeSessionCreateRequestClientSecret)

Ephemeral key returned by the API.

Source
input_audio_format

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

Source
input_audio_format=(input_audio_format : String | Nil)

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

Source
input_audio_transcription

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.

Source
input_audio_transcription=(input_audio_transcription : RealtimeSessionCreateRequestInputAudioTranscription | Nil)

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.

Source
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.

Source
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.

Source
max_response_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.

Source
max_response_output_tokens=(max_response_output_tokens : RealtimeSessionCreateRequestMaxResponseOutputTokens | 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.

Source
modalities

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

Source
modalities=(modalities : Hash(String, JSON::Any) | Nil)

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

Source
output_audio_format

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

Source
output_audio_format=(output_audio_format : String | Nil)

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

Source
prompt
Source
prompt=(prompt : Prompt | Nil)
Source
speed

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.

Source
speed=(speed : Float64 | Nil)

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.

Source
temperature

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

Source
temperature=(temperature : Float64 | Nil)

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

Source
tool_choice

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

Source
tool_choice=(tool_choice : String | Nil)

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

Source
tools

Tools (functions) available to the model.

Source
tools=(tools : Array(RealtimeSessionCreateRequestToolsItem) | Nil)

Tools (functions) available to the model.

Source
tracing

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.

Source
tracing=(tracing : RealtimeSessionCreateRequestTracing | Nil)

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.

Source
truncation
Source
truncation=(truncation : RealtimeTruncation | Nil)
Source
turn_detection

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.

Source
turn_detection=(turn_detection : RealtimeSessionCreateRequestTurnDetection | Nil)

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.

Source
voice

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.

Source
voice=(voice : VoiceIdsShared | Nil)

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.

Source