Table of Contents

Class RealtimeResponseCreateParams

Namespace
OpenAI.Realtime
Assembly
OpenAI-DotNet.dll

Create a new Realtime response with these parameters.

public sealed class RealtimeResponseCreateParams
Inheritance
RealtimeResponseCreateParams
Inherited Members

Constructors

RealtimeResponseCreateParams() 

public RealtimeResponseCreateParams()

RealtimeResponseCreateParams(Modality, string, string, RealtimeAudioFormat, IEnumerable<Tool>, string, float?, int?, ConversationResponseType, IReadOnlyDictionary<string, string>, IEnumerable<ConversationItem>)

Constructor.

public RealtimeResponseCreateParams(Modality modalities = Modality.Text | Modality.Audio, string instructions = null, string voice = null, RealtimeAudioFormat outputAudioFormat = RealtimeAudioFormat.PCM16, IEnumerable<Tool> tools = null, string toolChoice = null, float? temperature = null, int? maxResponseOutputTokens = null, ConversationResponseType conversation = ConversationResponseType.Auto, IReadOnlyDictionary<string, string> metadata = null, IEnumerable<ConversationItem> input = null)

Parameters

modalities Modality

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

instructions string

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.

voice string

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.

outputAudioFormat RealtimeAudioFormat

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

tools IEnumerable<Tool>

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

toolChoice string

How the model chooses tools. Options are auto, none, required, or specify a function, like {"type": "function", "function": {"name": "my_function"}}.

temperature float?

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

maxResponseOutputTokens int?

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.

conversation ConversationResponseType

Controls which conversation the response is added to. Currently, supports auto and none, with auto as the default value. The auto value means that the contents of the response will be added to the default conversation. Set this to none to create an out-of-band response which will not add items to default conversation.

metadata IReadOnlyDictionary<string, string>

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. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.

input IEnumerable<ConversationItem>

Input items to include in the prompt for the model. Using this field creates a new context for this Response instead of using the default conversation. An empty array [] will clear the context for this Response.
Note that this can include references to items from the default conversation.

Properties

Conversation

Controls which conversation the response is added to. Currently, supports auto and none, with auto as the default value. The auto value means that the contents of the response will be added to the default conversation. Set this to none to create an out-of-band response which will not add items to default conversation.

[JsonInclude]
[JsonPropertyName("conversation")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public ConversationResponseType Conversation { get; }

Property Value

ConversationResponseType

Input

Input items to include in the prompt for the model. Using this field creates a new context for this Response instead of using the default conversation. An empty array [] will clear the context for this Response.
Note that this can include references to items from the default conversation.

[JsonInclude]
[JsonPropertyName("input")]
[JsonIgnore(Condition = JsonIgnoreCondition.Never)]
public IReadOnlyList<ConversationItem> Input { get; }

Property Value

IReadOnlyList<ConversationItem>

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.

[JsonInclude]
[JsonPropertyName("instructions")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public string Instructions { get; }

Property Value

string

MaxResponseOutputTokens

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.

[JsonInclude]
[JsonPropertyName("max_response_output_tokens")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public object MaxResponseOutputTokens { get; }

Property Value

object

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. Keys can be a maximum of 64 characters long and values can be a maximum of 512 characters long.

[JsonInclude]
[JsonPropertyName("metadata")]
public IReadOnlyDictionary<string, string> Metadata { get; }

Property Value

IReadOnlyDictionary<string, string>

Modalities

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

[JsonInclude]
[JsonPropertyName("modalities")]
[JsonConverter(typeof(ModalityConverter))]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public Modality Modalities { get; }

Property Value

Modality

OutputAudioFormat

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

[JsonInclude]
[JsonPropertyName("output_audio_format")]
[JsonIgnore(Condition = JsonIgnoreCondition.Never)]
[JsonConverter(typeof(JsonStringEnumConverter<RealtimeAudioFormat>))]
public RealtimeAudioFormat OutputAudioFormat { get; }

Property Value

RealtimeAudioFormat

Temperature

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

[JsonInclude]
[JsonPropertyName("temperature")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public float? Temperature { get; }

Property Value

float?

ToolChoice

How the model chooses tools. Options are auto, none, required, or specify a function, like {"type": "function", "function": {"name": "my_function"}}.

[JsonInclude]
[JsonPropertyName("tool_choice")]
public object ToolChoice { get; }

Property Value

object

Tools

The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

[JsonInclude]
[JsonPropertyName("tools")]
public IReadOnlyList<Function> Tools { get; }

Property Value

IReadOnlyList<Function>

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.

[JsonInclude]
[JsonPropertyName("voice")]
[JsonIgnore(Condition = JsonIgnoreCondition.WhenWritingDefault)]
public string Voice { get; }

Property Value

string
Edit this page