update sample, readme, tests

Author: amber-yujueWang

sdk/cognitiveservices/azure-ai-speech-transcription/README.md

@@ -141,15 +141,11 @@ try {
     // Create transcription options
     TranscriptionOptions options = new TranscriptionOptions(audioFileDetails);
 
-    // Create transcribe request content
-    TranscriptionContent requestContent = new TranscriptionContent()
-        .setOptions(options);
-
     // Transcribe audio
-    TranscriptionResult result = client.transcribe(requestContent);
+    TranscriptionResult result = client.transcribe(options);
 
     // Process results
-    System.out.println("Duration: " + result.getDuration() + "ms");
+    System.out.println("Duration: " + result.getDuration() + " ms");
     result.getCombinedPhrases().forEach(phrase -> {
         System.out.println("Channel " + phrase.getChannel() + ": " + phrase.getText());
     });
@@ -171,12 +167,8 @@ TranscriptionClient client = new TranscriptionClientBuilder()
 // Create transcription options with audio URL
 TranscriptionOptions options = new TranscriptionOptions("https://example.com/audio.wav");
 
-// Create transcribe request content
-TranscriptionContent requestContent = new TranscriptionContent()
-    .setOptions(options);
-
 // Transcribe audio
-TranscriptionResult result = client.transcribe(requestContent);
+TranscriptionResult result = client.transcribe(options);
 
 // Process results
 result.getCombinedPhrases().forEach(phrase -> {
@@ -205,12 +197,8 @@ AudioFileDetails audioFileDetails = new AudioFileDetails(BinaryData.fromBytes(au
 // Create transcription options with AudioFileDetails
 TranscriptionOptions options = new TranscriptionOptions(audioFileDetails);
 
-// Create transcribe request content
-TranscriptionContent requestContent = new TranscriptionContent()
-    .setOptions(options);
-
 // Transcribe audio
-TranscriptionResult result = client.transcribe(requestContent);
+TranscriptionResult result = client.transcribe(options);
 
 // Process results
 result.getCombinedPhrases().forEach(phrase -> {
@@ -237,10 +225,7 @@ TranscriptionOptions options = new TranscriptionOptions(audioFileDetails)
     .setLocales(java.util.Arrays.asList("en-US"))
     .setEnhancedModeOptions(enhancedMode);
 
-TranscriptionContent requestContent = new TranscriptionContent()
-    .setOptions(options);
-
-TranscriptionResult result = client.transcribe(requestContent);
+TranscriptionResult result = client.transcribe(options);
 ```
 
 #### Enhanced mode with custom prompts
@@ -265,10 +250,7 @@ TranscriptionOptions options = new TranscriptionOptions(audioFileDetails)
     .setLocales(java.util.Arrays.asList("en-US"))
     .setEnhancedModeOptions(enhancedMode);
 
-TranscriptionContent requestContent = new TranscriptionContent()
-    .setOptions(options);
-
-TranscriptionResult result = client.transcribe(requestContent);
+TranscriptionResult result = client.transcribe(options);
 ```
 
 #### Enhanced mode with translation
@@ -289,10 +271,7 @@ TranscriptionOptions options = new TranscriptionOptions(audioFileDetails)
     .setLocales(java.util.Arrays.asList("es-ES")) // Source language: Spanish
     .setEnhancedModeOptions(enhancedMode);
 
-TranscriptionContent requestContent = new TranscriptionContent()
-    .setOptions(options);
-
-TranscriptionResult result = client.transcribe(requestContent);
+TranscriptionResult result = client.transcribe(options);
 ```
 
 ### Service API versions

sdk/cognitiveservices/azure-ai-speech-transcription/customization/src/main/java/SpeechTranscriptionCustomization.java

@@ -18,6 +18,7 @@
 import com.azure.core.exception.ResourceNotFoundException;
 import com.azure.core.http.rest.RequestOptions;
 import com.azure.core.http.rest.Response;
+import com.azure.core.http.rest.SimpleResponse;
 import com.azure.core.util.BinaryData;
 import com.azure.core.util.FluxUtil;
 import com.azure.core.util.logging.ClientLogger;
@@ -47,7 +48,7 @@ public final class TranscriptionAsyncClient {
     /**
      * Transcribes the provided audio stream.
      * <p><strong>Response Body Schema</strong></p>
-     * 
+     *
      * <pre>
      * {@code
      * {
@@ -114,7 +115,7 @@ Mono<TranscriptionResult> transcribe(TranscriptionContent body) {
         // Generated convenience method for transcribeWithResponse
         RequestOptions requestOptions = new RequestOptions();
         return transcribeWithResponse(
-            new MultipartFormDataHelper(requestOptions).serializeJsonField("definition", body.getOptions())
+            new MultipartFormDataHelper(requestOptions).serializeJsonField("options", body.getOptions())
                 .serializeFileField("audio", body.getAudio() == null ? null : body.getAudio().getContent(),
                     body.getAudio() == null ? null : body.getAudio().getContentType(),
                     body.getAudio() == null ? null : body.getAudio().getFilename())
@@ -136,10 +137,13 @@ Mono<TranscriptionResult> transcribe(TranscriptionContent body) {
      * @throws RuntimeException all other wrapped checked exceptions if the request fails to be sent.
      * @return the result of the transcribe operation on successful completion of Mono.
      */
+    // Customized method added via post-generation customization
     @ServiceMethod(returns = ReturnType.SINGLE)
     public Mono<TranscriptionResult> transcribe(TranscriptionOptions options) {
-        TranscriptionContent requestContent = new TranscriptionContent();
-        requestContent.setOptions(options);
+        TranscriptionContent requestContent = new TranscriptionContent(options);
+        if (options.getFileDetails() != null) {
+            requestContent.setAudio(options.getFileDetails());
+        }
         return transcribe(requestContent);
     }
 
@@ -155,35 +159,22 @@ public Mono<TranscriptionResult> transcribe(TranscriptionOptions options) {
      * @throws RuntimeException all other wrapped checked exceptions if the request fails to be sent.
      * @return the response containing the result of the transcribe operation on successful completion of Mono.
      */
+    // Customized method added via post-generation customization
     public Mono<Response<TranscriptionResult>> transcribeWithResponse(TranscriptionOptions options) {
-        TranscriptionContent requestContent = new TranscriptionContent();
-        requestContent.setOptions(options);
+        TranscriptionContent requestContent = new TranscriptionContent(options);
+        if (options.getFileDetails() != null) {
+            requestContent.setAudio(options.getFileDetails());
+        }
         RequestOptions requestOptions = new RequestOptions();
         return transcribeWithResponse(
-            new MultipartFormDataHelper(requestOptions).serializeJsonField("definition", requestContent.getOptions())
+            new MultipartFormDataHelper(requestOptions).serializeJsonField("options", requestContent.getOptions())
                 .serializeFileField("audio",
                     requestContent.getAudio() == null ? null : requestContent.getAudio().getContent(),
                     requestContent.getAudio() == null ? null : requestContent.getAudio().getContentType(),
                     requestContent.getAudio() == null ? null : requestContent.getAudio().getFilename())
                 .end()
                 .getRequestBody(),
-            requestOptions).map(response -> new Response<TranscriptionResult>() {
-
-                public int getStatusCode() {
-                    return response.getStatusCode();
-                }
-
-                public com.azure.core.http.HttpHeaders getHeaders() {
-                    return response.getHeaders();
-                }
-
-                public com.azure.core.http.HttpRequest getRequest() {
-                    return response.getRequest();
-                }
-
-                public TranscriptionResult getValue() {
-                    return response.getValue().toObject(TranscriptionResult.class);
-                }
-            });
+            requestOptions).map(
+                response -> new SimpleResponse<>(response, response.getValue().toObject(TranscriptionResult.class)));
     }
 }

sdk/cognitiveservices/azure-ai-speech-transcription/src/main/java/com/azure/ai/speech/transcription/TranscriptionAsyncClient.java

@@ -18,6 +18,7 @@
 import com.azure.core.exception.ResourceNotFoundException;
 import com.azure.core.http.rest.RequestOptions;
 import com.azure.core.http.rest.Response;
+import com.azure.core.http.rest.SimpleResponse;
 import com.azure.core.util.BinaryData;
 import com.azure.core.util.logging.ClientLogger;
 
@@ -45,7 +46,7 @@ public final class TranscriptionClient {
     /**
      * Transcribes the provided audio stream.
      * <p><strong>Response Body Schema</strong></p>
-     * 
+     *
      * <pre>
      * {@code
      * {
@@ -111,7 +112,7 @@ TranscriptionResult transcribe(TranscriptionContent body) {
         // Generated convenience method for transcribeWithResponse
         RequestOptions requestOptions = new RequestOptions();
         return transcribeWithResponse(
-            new MultipartFormDataHelper(requestOptions).serializeJsonField("definition", body.getOptions())
+            new MultipartFormDataHelper(requestOptions).serializeJsonField("options", body.getOptions())
                 .serializeFileField("audio", body.getAudio() == null ? null : body.getAudio().getContent(),
                     body.getAudio() == null ? null : body.getAudio().getContentType(),
                     body.getAudio() == null ? null : body.getAudio().getFilename())
@@ -120,6 +121,7 @@ TranscriptionResult transcribe(TranscriptionContent body) {
             requestOptions).getValue().toObject(TranscriptionResult.class);
     }
 
+    // Customized method added via post-generation customization
     /**
      * Transcribes the provided audio stream with the specified options.
      *
@@ -132,10 +134,13 @@ TranscriptionResult transcribe(TranscriptionContent body) {
      * @throws RuntimeException all other wrapped checked exceptions if the request fails to be sent.
      * @return the result of the transcribe operation.
      */
+    // Customized method added via post-generation customization
     @ServiceMethod(returns = ReturnType.SINGLE)
     public TranscriptionResult transcribe(TranscriptionOptions options) {
-        TranscriptionContent requestContent = new TranscriptionContent();
-        requestContent.setOptions(options);
+        TranscriptionContent requestContent = new TranscriptionContent(options);
+        if (options.getFileDetails() != null) {
+            requestContent.setAudio(options.getFileDetails());
+        }
         return transcribe(requestContent);
     }
 
@@ -151,36 +156,22 @@ public TranscriptionResult transcribe(TranscriptionOptions options) {
      * @throws RuntimeException all other wrapped checked exceptions if the request fails to be sent.
      * @return the response containing the result of the transcribe operation.
      */
+    // Customized method added via post-generation customization
     public Response<TranscriptionResult> transcribeWithResponse(TranscriptionOptions options) {
-        TranscriptionContent requestContent = new TranscriptionContent();
-        requestContent.setOptions(options);
+        TranscriptionContent requestContent = new TranscriptionContent(options);
+        if (options.getFileDetails() != null) {
+            requestContent.setAudio(options.getFileDetails());
+        }
         RequestOptions requestOptions = new RequestOptions();
         Response<BinaryData> response = transcribeWithResponse(
-            new MultipartFormDataHelper(requestOptions).serializeJsonField("definition", requestContent.getOptions())
+            new MultipartFormDataHelper(requestOptions).serializeJsonField("options", requestContent.getOptions())
                 .serializeFileField("audio",
                     requestContent.getAudio() == null ? null : requestContent.getAudio().getContent(),
                     requestContent.getAudio() == null ? null : requestContent.getAudio().getContentType(),
                     requestContent.getAudio() == null ? null : requestContent.getAudio().getFilename())
                 .end()
                 .getRequestBody(),
             requestOptions);
-        return new Response<TranscriptionResult>() {
-
-            public int getStatusCode() {
-                return response.getStatusCode();
-            }
-
-            public com.azure.core.http.HttpHeaders getHeaders() {
-                return response.getHeaders();
-            }
-
-            public com.azure.core.http.HttpRequest getRequest() {
-                return response.getRequest();
-            }
-
-            public TranscriptionResult getValue() {
-                return response.getValue().toObject(TranscriptionResult.class);
-            }
-        };
+        return new SimpleResponse<>(response, response.getValue().toObject(TranscriptionResult.class));
     }
 }

sdk/cognitiveservices/azure-ai-speech-transcription/src/main/java/com/azure/ai/speech/transcription/TranscriptionClient.java

@@ -12,13 +12,6 @@
 @Fluent
 public final class TranscriptionContent {
 
-    /*
-     * Metadata for a transcription request. This field contains a JSON-serialized object of type
-     * `TranscriptionOptions`.
-     */
-    @Generated
-    private TranscriptionOptions options;
-
     /*
      * The content of the audio file to be transcribed. The audio file must be shorter than 2 hours in audio duration
      * and smaller than 250 MB in size. Optional if audioUrl is provided in the definition.
@@ -27,57 +20,54 @@ public final class TranscriptionContent {
     private AudioFileDetails audio;
 
     /**
-     * Creates an instance of TranscriptionContent class.
+     * Get the audio property: The content of the audio file to be transcribed. The audio file must be shorter than 2
+     * hours in audio duration and smaller than 250 MB in size. Optional if audioUrl is provided in the definition.
+     *
+     * @return the audio value.
      */
     @Generated
-    public TranscriptionContent() {
+    public AudioFileDetails getAudio() {
+        return this.audio;
     }
 
     /**
-     * Get the options property: Metadata for a transcription request. This field contains a JSON-serialized object of
-     * type `TranscriptionOptions`.
+     * Set the audio property: The content of the audio file to be transcribed. The audio file must be shorter than 2
+     * hours in audio duration and smaller than 250 MB in size. Optional if audioUrl is provided in the definition.
      *
-     * @return the options value.
+     * @param audio the audio value to set.
+     * @return the TranscriptionContent object itself.
      */
     @Generated
-    public TranscriptionOptions getOptions() {
-        return this.options;
+    public TranscriptionContent setAudio(AudioFileDetails audio) {
+        this.audio = audio;
+        return this;
     }
 
     /**
-     * Set the options property: Metadata for a transcription request. This field contains a JSON-serialized object of
-     * type `TranscriptionOptions`.
+     * Creates an instance of TranscriptionContent class.
      *
      * @param options the options value to set.
-     * @return the TranscriptionContent object itself.
      */
     @Generated
-    public TranscriptionContent setOptions(TranscriptionOptions options) {
+    public TranscriptionContent(TranscriptionOptions options) {
         this.options = options;
-        return this;
     }
 
-    /**
-     * Get the audio property: The content of the audio file to be transcribed. The audio file must be shorter than 2
-     * hours in audio duration and smaller than 250 MB in size. Optional if audioUrl is provided in the definition.
-     *
-     * @return the audio value.
+    /*
+     * Metadata for a transcription request. This field contains a JSON-serialized object of type
+     * `TranscriptionOptions`.
      */
     @Generated
-    public AudioFileDetails getAudio() {
-        return this.audio;
-    }
+    private final TranscriptionOptions options;
 
     /**
-     * Set the audio property: The content of the audio file to be transcribed. The audio file must be shorter than 2
-     * hours in audio duration and smaller than 250 MB in size. Optional if audioUrl is provided in the definition.
+     * Get the options property: Metadata for a transcription request. This field contains a JSON-serialized object of
+     * type `TranscriptionOptions`.
      *
-     * @param audio the audio value to set.
-     * @return the TranscriptionContent object itself.
+     * @return the options value.
      */
     @Generated
-    public TranscriptionContent setAudio(AudioFileDetails audio) {
-        this.audio = audio;
-        return this;
+    public TranscriptionOptions getOptions() {
+        return this.options;
     }
 }

sdk/cognitiveservices/azure-ai-speech-transcription/src/main/java/com/azure/ai/speech/transcription/models/TranscriptionContent.java

@@ -285,7 +285,7 @@ public JsonWriter toJson(JsonWriter jsonWriter) throws IOException {
     @Generated
     public static TranscriptionOptions fromJson(JsonReader jsonReader) throws IOException {
         return jsonReader.readObject(reader -> {
-            TranscriptionOptions deserializedTranscriptionOptions = new TranscriptionOptions();
+            TranscriptionOptions deserializedTranscriptionOptions = new TranscriptionOptions((String) null);
             while (reader.nextToken() != JsonToken.END_OBJECT) {
                 String fieldName = reader.getFieldName();
                 reader.nextToken();
@@ -294,7 +294,7 @@ public static TranscriptionOptions fromJson(JsonReader jsonReader) throws IOExce
                 } else if ("locales".equals(fieldName)) {
                     List<String> locales = reader.readArray(reader1 -> reader1.getString());
                     deserializedTranscriptionOptions.locales = locales;
-                } else if ("models".equals(fieldName)) {
+                } else if ("localeModelMapping".equals(fieldName)) {
                     Map<String, String> localeModelMapping = reader.readMap(reader1 -> reader1.getString());
                     deserializedTranscriptionOptions.localeModelMapping = localeModelMapping;
                 } else if ("profanityFilterMode".equals(fieldName)) {
@@ -338,4 +338,13 @@ public TranscriptionOptions(String audioUrl) {
     public TranscriptionOptions(AudioFileDetails fileDetails) {
         this.audioFileDetails = fileDetails;
     }
+
+    /**
+     * Get the audioFileDetails property: The audio file details for transcription.
+     *
+     * @return the audioFileDetails value.
+     */
+    public AudioFileDetails getFileDetails() {
+        return this.audioFileDetails;
+    }
 }

sdk/cognitiveservices/azure-ai-speech-transcription/src/main/java/com/azure/ai/speech/transcription/models/TranscriptionOptions.java

@@ -276,7 +276,7 @@ private static void demonstrateTaskSpecificEnhancedMode(String endpoint, String
             if (result.getPhrases() != null && !result.getPhrases().isEmpty()) {
                 System.out.println("\nTranscription phrases:");
                 result.getPhrases().forEach(phrase ->
-                    System.out.println("  [" + phrase.getOffset() + "ms] " + phrase.getText())
+                    System.out.println("  [" + phrase.getOffset() + " ms] " + phrase.getText())
                 );
             }
             System.out.println();