.Net: Copy AzureOpenAITextToAudioService related code to AzureOpenAI project

dotnet/src/Connectors/Connectors.AzureOpenAI/Connectors.AzureOpenAI.csproj

@@ -21,10 +21,20 @@
     <Description>Semantic Kernel connectors for Azure OpenAI. Contains clients for text generation, chat completion, embedding and DALL-E text to image.</Description>
   </PropertyGroup>
 
+  <ItemGroup>
+    <Compile Remove="Core\ClientCore.TextToAudio.cs" />
+    <Compile Remove="Services\AzureOpenAITextToAudioService.cs" />
+  </ItemGroup>
+
   <ItemGroup>
     <InternalsVisibleTo Include="SemanticKernel.Connectors.AzureOpenAI.UnitTests" />
   </ItemGroup>
 
+  <ItemGroup>
+    <None Include="Core\ClientCore.TextToAudio.cs" />
+    <None Include="Services\AzureOpenAITextToAudioService.cs" />
+  </ItemGroup>
+
   <ItemGroup>
     <PackageReference Include="Azure.AI.OpenAI" VersionOverride="2.0.0-beta.2" />
   </ItemGroup>

dotnet/src/Connectors/Connectors.AzureOpenAI/Core/ClientCore.TextToAudio.cs

@@ -0,0 +1,67 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System;
+using System.ClientModel;
+using System.Collections.Generic;
+using System.Threading;
+using System.Threading.Tasks;
+using OpenAI.Audio;
+
+namespace Microsoft.SemanticKernel.Connectors.AzureOpenAI;
+
+/// <summary>
+/// Base class for AI clients that provides common functionality for interacting with Azure OpenAI services.
+/// </summary>
+internal partial class ClientCore
+{
+    /// <summary>
+    /// Generates an image with the provided configuration.
+    /// </summary>
+    /// <param name="prompt">Prompt to generate the image</param>
+    /// <param name="executionSettings">Text to Audio execution settings for the prompt</param>
+    /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
+    /// <returns>Url of the generated image</returns>
+    internal async Task<IReadOnlyList<AudioContent>> GetAudioContentsAsync(
+        string prompt,
+        PromptExecutionSettings? executionSettings,
+        CancellationToken cancellationToken)
+    {
+        Verify.NotNullOrWhiteSpace(prompt);
+
+        OpenAITextToAudioExecutionSettings? audioExecutionSettings = OpenAITextToAudioExecutionSettings.FromExecutionSettings(executionSettings);
+        var (responseFormat, mimeType) = GetGeneratedSpeechFormatAndMimeType(audioExecutionSettings?.ResponseFormat);
+        SpeechGenerationOptions options = new()
+        {
+            ResponseFormat = responseFormat,
+            Speed = audioExecutionSettings?.Speed,
+        };
+
+        ClientResult<BinaryData> response = await RunRequestAsync(() => this.Client.GetAudioClient(this.ModelId).GenerateSpeechFromTextAsync(prompt, GetGeneratedSpeechVoice(audioExecutionSettings?.Voice), options, cancellationToken)).ConfigureAwait(false);
+
+        return [new AudioContent(response.Value.ToArray(), mimeType)];
+    }
+
+    private static GeneratedSpeechVoice GetGeneratedSpeechVoice(string? voice)
+        => voice?.ToUpperInvariant() switch
+        {
+            "ALLOY" => GeneratedSpeechVoice.Alloy,
+            "ECHO" => GeneratedSpeechVoice.Echo,
+            "FABLE" => GeneratedSpeechVoice.Fable,
+            "ONYX" => GeneratedSpeechVoice.Onyx,
+            "NOVA" => GeneratedSpeechVoice.Nova,
+            "SHIMMER" => GeneratedSpeechVoice.Shimmer,
+            _ => throw new NotSupportedException($"The voice '{voice}' is not supported."),
+        };
+
+    private static (GeneratedSpeechFormat Format, string MimeType) GetGeneratedSpeechFormatAndMimeType(string? format)
+        => format?.ToUpperInvariant() switch
+        {
+            "WAV" => (GeneratedSpeechFormat.Wav, "audio/wav"),
+            "MP3" => (GeneratedSpeechFormat.Mp3, "audio/mpeg"),
+            "OPUS" => (GeneratedSpeechFormat.Opus, "audio/opus"),
+            "FLAC" => (GeneratedSpeechFormat.Flac, "audio/flac"),
+            "AAC" => (GeneratedSpeechFormat.Aac, "audio/aac"),
+            "PCM" => (GeneratedSpeechFormat.Pcm, "audio/l16"),
+            _ => throw new NotSupportedException($"The format '{format}' is not supported.")
+        };
+}

dotnet/src/Connectors/Connectors.AzureOpenAI/Services/AzureOpenAITextToAudioService.cs

@@ -0,0 +1,63 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+using System.Collections.Generic;
+using System.Diagnostics.CodeAnalysis;
+using System.Net.Http;
+using System.Threading;
+using System.Threading.Tasks;
+using Microsoft.Extensions.Logging;
+using Microsoft.SemanticKernel.Services;
+using Microsoft.SemanticKernel.TextToAudio;
+
+namespace Microsoft.SemanticKernel.Connectors.AzureOpenAI;
+
+/// <summary>
+/// Azure OpenAI text-to-audio service.
+/// </summary>
+[Experimental("SKEXP0001")]
+public sealed class AzureOpenAITextToAudioService : ITextToAudioService
+{
+    /// <summary>
+    /// Azure OpenAI text-to-audio client for HTTP operations.
+    /// </summary>
+    private readonly AzureOpenAITextToAudioClient _client;
+
+    /// <inheritdoc/>
+    public IReadOnlyDictionary<string, object?> Attributes => this._client.Attributes;
+
+    /// <summary>
+    /// Gets the key used to store the deployment name in the <see cref="IAIService.Attributes"/> dictionary.
+    /// </summary>
+    public static string DeploymentNameKey => "DeploymentName";
+
+    /// <summary>
+    /// Creates an instance of the <see cref="AzureOpenAITextToAudioService"/> connector with API key auth.
+    /// </summary>
+    /// <param name="deploymentName">Azure OpenAI deployment name, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="endpoint">Azure OpenAI deployment URL, see https://learn.microsoft.com/azure/cognitive-services/openai/quickstart</param>
+    /// <param name="apiKey">Azure OpenAI API key, see https://learn.microsoft.com/azure/cognitive-services/openai/quickstart</param>
+    /// <param name="modelId">Azure OpenAI model id, see https://learn.microsoft.com/azure/cognitive-services/openai/how-to/create-resource</param>
+    /// <param name="httpClient">Custom <see cref="HttpClient"/> for HTTP requests.</param>
+    /// <param name="loggerFactory">The <see cref="ILoggerFactory"/> to use for logging. If null, no logging will be performed.</param>
+    public AzureOpenAITextToAudioService(
+        string deploymentName,
+        string endpoint,
+        string apiKey,
+        string? modelId = null,
+        HttpClient? httpClient = null,
+        ILoggerFactory? loggerFactory = null)
+    {
+        this._client = new(deploymentName, endpoint, apiKey, modelId, httpClient, loggerFactory?.CreateLogger(typeof(AzureOpenAITextToAudioService)));
+
+        this._client.AddAttribute(DeploymentNameKey, deploymentName);
+        this._client.AddAttribute(AIServiceExtensions.ModelIdKey, modelId);
+    }
+
+    /// <inheritdoc/>
+    public Task<IReadOnlyList<AudioContent>> GetAudioContentsAsync(
+        string text,
+        PromptExecutionSettings? executionSettings = null,
+        Kernel? kernel = null,
+        CancellationToken cancellationToken = default)
+        => this._client.GetAudioContentsAsync(text, executionSettings, cancellationToken);
+}