update batch transcription samples for API version 2024-11-15 (#2665)

* update sample

samples/batch/csharp/batchclient/BatchClient.csproj

@@ -24,8 +24,8 @@
     <WarningLevel>4</WarningLevel>
   </PropertyGroup>
   <ItemGroup>
-    <PackageReference Include="Microsoft.AspNet.WebApi.Client" version="5.2.9" PrivateAssets="All" />
-    <PackageReference Include="Newtonsoft.Json" version="13.0.2" PrivateAssets="All" />
+    <PackageReference Include="Microsoft.AspNet.WebApi.Client" version="6.0.0" PrivateAssets="All" />
+    <PackageReference Include="Newtonsoft.Json" version="13.0.3" PrivateAssets="All" />
     <PackageReference Include="Polly" version="7.2.3" PrivateAssets="All" />
   </ItemGroup>
 </Project>

samples/batch/csharp/batchclient/batchclient.cs

@@ -20,6 +20,7 @@ public partial class BatchClient : IDisposable
 
         private readonly HttpClient client;
         private readonly string speechToTextBasePath;
+        private readonly string apiVersion;
 
         private static AsyncRetryPolicy<HttpResponseMessage> transientFailureRetryingPolicy = Policy
             .Handle<HttpRequestException>()
@@ -30,21 +31,22 @@ public partial class BatchClient : IDisposable
                 Console.WriteLine($"Request failed with {result.Exception?.ToString() ?? result.Result?.StatusCode.ToString()}. Waiting {timeSpan} before next retry. Retry attempt {retryCount}");
             });
 
-        private BatchClient(HttpClient client)
+        private BatchClient(HttpClient client, string apiVersion)
         {
             this.client = client;
-            speechToTextBasePath = "speechtotext/v3.2/";
+            this.speechToTextBasePath = "speechtotext/";
+            this.apiVersion = apiVersion;
         }
 
-        public static BatchClient CreateApiV3Client(string key, string hostName)
+        public static BatchClient CreateApiClient(string key, string hostName, string apiVersion)
         {
             var client = new HttpClient();
             client.Timeout = TimeSpan.FromMinutes(25);
             client.BaseAddress = new UriBuilder(Uri.UriSchemeHttps, hostName).Uri;
 
             client.DefaultRequestHeaders.Add("Ocp-Apim-Subscription-Key", key);
 
-            return new BatchClient(client);
+            return new BatchClient(client, apiVersion);
         }
 
         private async Task<TResponse> PostAsJsonAsync<TPayload, TResponse>(string path, TPayload payload)

samples/batch/csharp/batchclient/batchclient.transcriptions.cs

@@ -13,7 +13,7 @@ public partial class BatchClient
     {
         public Task<PaginatedTranscriptions> GetTranscriptionsAsync()
         {
-            var path = $"{this.speechToTextBasePath}transcriptions";
+            var path = $"{this.speechToTextBasePath}transcriptions?api-version={this.apiVersion}";
             return this.GetAsync<PaginatedTranscriptions>(path);
         }
 
@@ -69,7 +69,7 @@ public Task<Transcription> CreateTranscriptionAsync(Transcription transcription)
                 throw new ArgumentNullException(nameof(transcription));
             }
 
-            var path = $"{this.speechToTextBasePath}transcriptions/";
+            var path = $"{this.speechToTextBasePath}transcriptions:submit?api-version={this.apiVersion}";
 
             return this.PostAsJsonAsync<Transcription, Transcription>(path, transcription);
         }

samples/batch/csharp/batchclient/dto/diarizationproperties.cs

@@ -7,6 +7,8 @@ namespace BatchClient
 {
     public class DiarizationProperties
     {
-        public DiarizationSpeakersProperties Speakers { get; set; }
+        public int MaxSpeakers { get; set; }
+
+        public bool Enabled { get; set; }
     }
 }

samples/batch/csharp/batchclient/dto/transcriptionproperties.cs

@@ -11,9 +11,6 @@ namespace BatchClient
 
     public class TranscriptionProperties
     {
-        [JsonProperty(PropertyName = "diarizationEnabled")]
-        public bool IsDiarizationEnabled { get; set; }
-
         [JsonProperty(PropertyName = "wordLevelTimestampsEnabled")]
         public bool IsWordLevelTimestampsEnabled { get; set; }
 
@@ -33,8 +30,7 @@ public class TranscriptionProperties
 
         public Uri DestinationContainerUrl { get; set; }
 
-        [JsonConverter(typeof(TimeSpanConverter))]
-        public TimeSpan TimeToLive { get; set; }
+        public int TimeToLiveHours { get; set; }
 
         public DiarizationProperties Diarization { get; set; }
 

samples/batch/csharp/batchclient/program.cs

@@ -47,7 +47,7 @@ static void Main(string[] args)
         private static async Task RunAsync()
         {
             // create the client object and authenticate
-            using (var client = BatchClient.CreateApiV3Client(SubscriptionKey, $"{Region}.api.cognitive.microsoft.com"))
+            using (var client = BatchClient.CreateApiClient(SubscriptionKey, $"{Region}.api.cognitive.microsoft.com", "2024-11-15"))
             {
                 // uncomment next line when using web hooks
                 // await SetupWebHookAsync(client).ConfigureAwait(false);
@@ -96,19 +96,15 @@ private async static Task TranscribeAsync(BatchClient client)
                 Model = CustomModel,
                 Properties = new TranscriptionProperties
                 {
-                    TimeToLive = TimeSpan.FromDays(1),
+                    TimeToLiveHours = 6,
                     IsWordLevelTimestampsEnabled = true,
                     IsDisplayFormWordLevelTimestampsEnabled = false,
 
                     // uncomment the following block to enable and configure speaker separation
-                    // IsDiarizationEnabled = true,
                     // Diarization = new DiarizationProperties
                     // {
-                    //     Speakers = new DiarizationSpeakersProperties
-                    //     {
-                    //         MinCount = 1,
-                    //         MaxCount = 5
-                    //     }
+                    //     Enabled = true,
+                    //     MaxSpeakers = 5
                     // },
 
                     // // uncomment the following block to enable and configure language identification prior to transcription. Available modes are "Single" and "Continuous".

samples/batch/csharp/webhookreceiver/webhookreceiver.cs

@@ -92,7 +92,7 @@ public static async Task<IActionResult> Run(
             // invocationId can be used for deduplication, it's unique per notification event
             logger.LogInformation($"Processing notification {webHookNotification.InvocationId}.");
 
-            using (var client = BatchClient.CreateApiV3Client(Program.SubscriptionKey, $"{Program.Region}.api.cognitive.microsoft.com"))
+            using (var client = BatchClient.CreateApiClient(Program.SubscriptionKey, $"{Program.Region}.api.cognitive.microsoft.com", "2024-11-15"))
             {
                 if (eventKind == WebHookEventKind.TranscriptionCompletion)
                 {

samples/batch/csharp/webhookreceiver/webhookreceiver.csproj

@@ -5,8 +5,8 @@
     <RootNamespace>WebHookReceiver</RootNamespace>
   </PropertyGroup>
   <ItemGroup>
-    <PackageReference Include="Microsoft.NET.Sdk.Functions" Version="4.1.3" />
-    <PackageReference Include="Newtonsoft.Json" Version="13.0.2" />
+    <PackageReference Include="Microsoft.NET.Sdk.Functions" Version="4.6.0" />
+    <PackageReference Include="Newtonsoft.Json" Version="13.0.3" />
   </ItemGroup>
   <ItemGroup>
     <ProjectReference Include="..\batchclient\batchclient.csproj" />

samples/batch/python/README.md

@@ -8,7 +8,7 @@ Follow these steps for the installation:
 
 1. Go to https://editor.swagger.io.
 1. Click **File**, then click **Import URL**.
-1. Enter the Swagger URL for the Speech Services API: `https://raw.githubusercontent.com/Azure/azure-rest-api-specs/main/specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/v3.2/speechtotext.json`.
+1. Enter the Swagger URL for the Speech Services API: `https://raw.githubusercontent.com/Azure/azure-rest-api-specs/main/specification/cognitiveservices/data-plane/Speech/SpeechToText/stable/2024-11-15/speechtotext.json`.
 1. Click **Generate Client** and select **Python**.
 1. Save the client library.
 1. Extract the downloaded python-client-generated.zip somewhere in your file system.

samples/batch/python/python-client/main.py

@@ -13,6 +13,8 @@
 logging.basicConfig(stream=sys.stdout, level=logging.DEBUG,
         format="%(asctime)s %(message)s", datefmt="%m/%d/%Y %I:%M:%S %p %Z")
 
+API_VERSION = "2024-11-15"
+
 # Your subscription key and region for the speech service
 SUBSCRIPTION_KEY = "YourSubscriptionKey"
 SERVICE_REGION = "YourServiceRegion"
@@ -132,7 +134,7 @@ def transcribe():
     # configure API key authorization: subscription_key
     configuration = swagger_client.Configuration()
     configuration.api_key["Ocp-Apim-Subscription-Key"] = SUBSCRIPTION_KEY
-    configuration.host = f"https://{SERVICE_REGION}.api.cognitive.microsoft.com/speechtotext/v3.2"
+    configuration.host = f"https://{SERVICE_REGION}.api.cognitive.microsoft.com/speechtotext"
 
     # create the client object and authenticate
     client = swagger_client.ApiClient(configuration)
@@ -143,13 +145,12 @@ def transcribe():
     # Specify transcription properties by passing a dict to the properties parameter. See
     # https://learn.microsoft.com/azure/cognitive-services/speech-service/batch-transcription-create?pivots=rest-api#request-configuration-options
     # for supported parameters.
-    properties = swagger_client.TranscriptionProperties()
+    properties = swagger_client.TranscriptionProperties(time_to_live_hours=6)
     # properties.word_level_timestamps_enabled = True
     # properties.display_form_word_level_timestamps_enabled = True
     # properties.punctuation_mode = "DictatedAndAutomatic"
     # properties.profanity_filter_mode = "Masked"
     # properties.destination_container_url = "<SAS Uri with at least write (w) permissions for an Azure Storage blob container that results should be written to>"
-    # properties.time_to_live = "PT1H"
 
     # uncomment the following block to enable and configure speaker separation
     # properties.diarization_enabled = True
@@ -169,10 +170,10 @@ def transcribe():
     # Uncomment this block to transcribe all files from a container.
     # transcription_definition = transcribe_from_container(RECORDINGS_CONTAINER_URI, properties)
 
-    created_transcription, status, headers = api.transcriptions_create_with_http_info(transcription=transcription_definition)
+    created_transcription, status, headers = api.transcriptions_submit_with_http_info(body=transcription_definition, api_version=API_VERSION)
 
     # get the transcription Id from the location URI
-    transcription_id = headers["location"].split("/")[-1]
+    transcription_id = headers["location"].split("/")[-1].split("?")[0]
 
     # Log information about the created transcription. If you should ask for support, please
     # include this information.
@@ -186,7 +187,7 @@ def transcribe():
         # wait for 5 seconds before refreshing the transcription status
         time.sleep(5)
 
-        transcription = api.transcriptions_get(transcription_id)
+        transcription = api.transcriptions_get(transcription_id, api_version=API_VERSION)
         logging.info(f"Transcriptions status: {transcription.status}")
 
         if transcription.status in ("Failed", "Succeeded"):
@@ -197,7 +198,7 @@ def transcribe():
                 logging.info("Transcription succeeded. Results are located in your Azure Blob Storage.")
                 break
 
-            pag_files = api.transcriptions_list_files(transcription_id)
+            pag_files = api.transcriptions_list_files(transcription_id, api_version=API_VERSION)
             for file_data in _paginate(api, pag_files):
                 if file_data.kind != "Transcription":
                     continue