class

OpenAI::RealtimeSession

Inherits JSON::Serializable < Reference < Object

Realtime session object for the beta interface.

Constructors

new(pull : JSON::PullParser)

new(id : String | Nil = nil, object : RealtimeSessionObject | Nil = nil, modalities : Hash(String, JSON::Any) | Nil = nil, model : RealtimeSessionModel | Nil = nil, instructions : String | Nil = nil, voice : VoiceIdsShared | Nil = nil, input_audio_format : RealtimeSessionInputAudioFormat | Nil = nil, output_audio_format : RealtimeSessionOutputAudioFormat | Nil = nil, input_audio_transcription : RealtimeSessionInputAudioTranscription | Nil = nil, turn_detection : RealtimeTurnDetection | Nil = nil, input_audio_noise_reduction : RealtimeSessionInputAudioNoiseReduction | Nil = nil, speed : Float64 | Nil = nil, tracing : RealtimeSessionTracing | Nil = nil, tools : Array(RealtimeFunctionTool) | Nil = nil, tool_choice : String | Nil = nil, temperature : Float64 | Nil = nil, max_response_output_tokens : RealtimeSessionMaxResponseOutputTokens | Nil = nil, expires_at : Int64 | Nil = nil, prompt : RealtimeSessionPrompt | Nil = nil, include_value : RealtimeSessionInclude | Nil = nil)

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

Instance methods

expires_at

Expiration timestamp for the session, in seconds since epoch.

expires_at=(expires_at : Int64 | Nil)

Expiration timestamp for the session, in seconds since epoch.

id

Unique identifier for the session that looks like sess_1234567890abcdef.

id=(id : String | Nil)

Unique identifier for the session that looks like sess_1234567890abcdef.

include_value

include_value=(include_value : RealtimeSessionInclude | Nil)

input_audio_format

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

input_audio_format=(input_audio_format : RealtimeSessionInputAudioFormat | Nil)

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

input_audio_noise_reduction

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

input_audio_noise_reduction=(input_audio_noise_reduction : RealtimeSessionInputAudioNoiseReduction | Nil)

Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

input_audio_transcription

input_audio_transcription=(input_audio_transcription : RealtimeSessionInputAudioTranscription | Nil)

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_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.

max_response_output_tokens=(max_response_output_tokens : RealtimeSessionMaxResponseOutputTokens | 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.

modalities

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

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

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

model

The Realtime model used for this session.

model=(model : RealtimeSessionModel | Nil)

The Realtime model used for this session.

object

The object type. Always realtime.session.

object=(object : RealtimeSessionObject | Nil)

The object type. Always realtime.session.

output_audio_format

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, output audio is sampled at a rate of 24kHz.

output_audio_format=(output_audio_format : RealtimeSessionOutputAudioFormat | Nil)

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, output audio is sampled at a rate of 24kHz.

prompt

prompt=(prompt : RealtimeSessionPrompt | Nil)

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.

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.

temperature

Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance.

temperature=(temperature : Float64 | Nil)

Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance.

tool_choice

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

tool_choice=(tool_choice : String | Nil)

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

tools

Tools (functions) available to the model.

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

Tools (functions) available to the model.

tracing

tracing=(tracing : RealtimeSessionTracing | Nil)

turn_detection

turn_detection=(turn_detection : RealtimeTurnDetection | Nil)

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.

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.