Class AudioEndpoint

Namespace

OpenAI.Audio

Assembly

OpenAI-DotNet.dll

Transforms audio into text.
https://platform.openai.com/docs/api-reference/audio

public sealed class AudioEndpoint : OpenAIBaseEndpoint

Inheritance

object

OpenAIBaseEndpoint

AudioEndpoint

Inherited Members

OpenAIBaseEndpoint.EnableDebug

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Constructors

AudioEndpoint(OpenAIClient)

public AudioEndpoint(OpenAIClient client)

Parameters

client OpenAIClient

Properties

IsAzureDeployment

Indicates if the endpoint has an Azure Deployment.

protected override bool? IsAzureDeployment { get; }

Property Value

bool?

Remarks

If the endpoint is an Azure deployment, is true. If it is not an Azure deployment, is false. If it is not an Azure supported Endpoint, is null.

Root

The root endpoint address.

protected override string Root { get; }

Property Value

string

Methods

CreateSpeechAsync(SpeechRequest, Func<ReadOnlyMemory<byte>, Task>, CancellationToken)

Generates audio from the input text.

public Task<ReadOnlyMemory<byte>> CreateSpeechAsync(SpeechRequest request, Func<ReadOnlyMemory<byte>, Task> chunkCallback = null, CancellationToken cancellationToken = default)

Parameters

request SpeechRequest

SpeechRequest.

chunkCallback Func<ReadOnlyMemory<byte>, Task>

Optional, partial chunk ReadOnlyMemory<T> callback to stream audio as it arrives.

cancellationToken CancellationToken

Optional, CancellationToken.

Returns

Task<ReadOnlyMemory<byte>>

ReadOnlyMemory<T>.

CreateTranscriptionJsonAsync(AudioTranscriptionRequest, CancellationToken)

Transcribes audio into the input language.

public Task<AudioResponse> CreateTranscriptionJsonAsync(AudioTranscriptionRequest request, CancellationToken cancellationToken = default)

Parameters

request AudioTranscriptionRequest

AudioTranscriptionRequest.

cancellationToken CancellationToken

Optional, CancellationToken.

Returns

Task<AudioResponse>

AudioResponse.

Remarks

This method expects the request format to be either Json or Verbose_Json.

CreateTranscriptionTextAsync(AudioTranscriptionRequest, CancellationToken)

Transcribes audio into the input language.

public Task<string> CreateTranscriptionTextAsync(AudioTranscriptionRequest request, CancellationToken cancellationToken = default)

Parameters

request AudioTranscriptionRequest

AudioTranscriptionRequest.

cancellationToken CancellationToken

Optional, CancellationToken.

Returns

Task<string>

The transcribed text.

CreateTranslationJsonAsync(AudioTranslationRequest, CancellationToken)

Translates audio into English.

public Task<AudioResponse> CreateTranslationJsonAsync(AudioTranslationRequest request, CancellationToken cancellationToken = default)

Parameters

request AudioTranslationRequest

cancellationToken CancellationToken

Returns

Task<AudioResponse>

Exceptions

ArgumentException

CreateTranslationTextAsync(AudioTranslationRequest, CancellationToken)

Translates audio into English.

public Task<string> CreateTranslationTextAsync(AudioTranslationRequest request, CancellationToken cancellationToken = default)

Parameters

request AudioTranslationRequest

cancellationToken CancellationToken

Returns

Task<string>

The translated text.