Table of Contents

Class InputAudioBufferAppendRequest

Namespace
OpenAI.Realtime
Assembly
OpenAI-DotNet.dll

Send this event to append audio bytes to the input audio buffer. The audio buffer is temporary storage you can write to and later commit. In Server VAD mode, the audio buffer is used to detect speech and the server will decide when to commit. When Server VAD is disabled, you must commit the audio buffer manually. The client may choose how much audio to place in each event up to a maximum of 15 MiB, for example streaming smaller chunks from the client may allow the VAD to be more responsive. Unlike made other client events, the server will not send a confirmation response to this event.

public sealed class InputAudioBufferAppendRequest : BaseRealtimeEvent, IClientEvent, IRealtimeEvent
Inheritance
InputAudioBufferAppendRequest
Implements
Inherited Members

Constructors

InputAudioBufferAppendRequest(byte[])

public InputAudioBufferAppendRequest(byte[] audioData)

Parameters

audioData byte[]

InputAudioBufferAppendRequest(ReadOnlyMemory<byte>)

public InputAudioBufferAppendRequest(ReadOnlyMemory<byte> audioData)

Parameters

audioData ReadOnlyMemory<byte>

InputAudioBufferAppendRequest(ReadOnlySpan<byte>)

public InputAudioBufferAppendRequest(ReadOnlySpan<byte> audioData)

Parameters

audioData ReadOnlySpan<byte>

Properties

Audio

Base64-encoded audio bytes. This must be in the format specified by the input_audio_format field in the session configuration.

[JsonInclude]
[JsonPropertyName("audio")]
public string Audio { get; }

Property Value

string

EventId

The unique ID of the server event.

[JsonInclude]
[JsonPropertyName("event_id")]
public override string EventId { get; }

Property Value

string

Type

[JsonInclude]
[JsonPropertyName("type")]
public override string Type { get; protected set; }

Property Value

string