switch default voice, Andrew -> AndrewMultilingual, notes Ava-> AvaMu…

…ltilingual (#2307)

Co-authored-by: Huaiping Ming <[email protected]>

quickstart/cpp/linux/text-to-speech/helloworld.cpp

@@ -17,7 +17,7 @@ void synthesizeSpeech()
     auto config = SpeechConfig::FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
     // Set the voice name, refer to https://aka.ms/speech/voices/neural for full list.
-    config->SetSpeechSynthesisVoiceName("en-US-AvaNeural");
+    config->SetSpeechSynthesisVoiceName("en-US-AvaMultilingualNeural");
 
     // Creates a speech synthesizer using the default speaker as audio output. The default spoken language is "en-us".
     auto synthesizer = SpeechSynthesizer::FromConfig(config);

quickstart/cpp/macos/text-to-speech/helloworld.cpp

@@ -17,7 +17,7 @@ void synthesizeSpeech()
     auto config = SpeechConfig::FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
     // Set the voice name, refer to https://aka.ms/speech/voices/neural for full list.
-    config->SetSpeechSynthesisVoiceName("en-US-AvaNeural");
+    config->SetSpeechSynthesisVoiceName("en-US-AvaMultilingualNeural");
 
     // Creates a speech synthesizer using the default speaker as audio output. The default spoken language is "en-us".
     auto synthesizer = SpeechSynthesizer::FromConfig(config);

quickstart/cpp/windows/text-to-speech/helloworld/helloworld.cpp

@@ -18,7 +18,7 @@ void synthesizeSpeech()
     auto config = SpeechConfig::FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
     // Set the voice name, refer to https://aka.ms/speech/voices/neural for full list.
-    config->SetSpeechSynthesisVoiceName("en-US-AvaNeural");
+    config->SetSpeechSynthesisVoiceName("en-US-AvaMultilingualNeural");
 
     // Creates a speech synthesizer using the default speaker as audio output. The default spoken language is "en-us".
     auto synthesizer = SpeechSynthesizer::FromConfig(config);

quickstart/csharp/dotnet/text-to-speech/helloworld/Program.cs

@@ -27,7 +27,7 @@ public static async Task SynthesisToSpeakerAsync()
             var config = SpeechConfig.FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
             // Set the voice name, refer to https://aka.ms/speech/voices/neural for full list.
-            config.SpeechSynthesisVoiceName = "en-US-AvaNeural";
+            config.SpeechSynthesisVoiceName = "en-US-AvaMultilingualNeural";
 
             // Creates a speech synthesizer using the default speaker as audio output.
             using (var synthesizer = new SpeechSynthesizer(config))

quickstart/csharp/dotnetcore/text-to-speech/helloworld/Program.cs

@@ -27,7 +27,7 @@ public static async Task SynthesisToSpeakerAsync()
             var config = SpeechConfig.FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
             // Set the voice name, refer to https://aka.ms/speech/voices/neural for full list.
-            config.SpeechSynthesisVoiceName = "en-US-AvaNeural";
+            config.SpeechSynthesisVoiceName = "en-US-AvaMultilingualNeural";
 
 
             // Creates a speech synthesizer using the default speaker as audio output.

quickstart/java/jre/text-to-speech/src/speechsdk/quickstart/Main.java

@@ -30,7 +30,7 @@ public static void main(String[] args) {
         try (SpeechConfig config = SpeechConfig.fromSubscription(speechSubscriptionKey, serviceRegion)) {
             // Set the voice name, refer to https://aka.ms/speech/voices/neural for full
             // list.
-            config.setSpeechSynthesisVoiceName("en-US-AvaNeural");
+            config.setSpeechSynthesisVoiceName("en-US-AvaMultilingualNeural");
             try (SpeechSynthesizer synth = new SpeechSynthesizer(config)) {
 
                 assert (config != null);

quickstart/python/text-to-speech/quickstart.py

@@ -10,7 +10,7 @@
 speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
 
 # Set the voice name, refer to https://aka.ms/speech/voices/neural for full list.
-speech_config.speech_synthesis_voice_name = "en-US-AvaNeural"
+speech_config.speech_synthesis_voice_name = "en-US-AvaMultilingualNeural"
 
 # Creates a speech synthesizer using the default speaker as audio output.
 speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config)

samples/batch-synthesis/csharp/BatchSynthesisSample/Program.cs

@@ -38,7 +38,7 @@
 
 // Create a new synthesis task with plain text
 var newSynthesisUri = await synthesisClient.CreateSynthesisAsync(
-    "en-US-AvaNeural",
+    "en-US-AvaMultilingualNeural",
     "sample batch synthesis",
     "sample description",
     sampleScript,

samples/batch-synthesis/python/synthesis.py

@@ -46,7 +46,7 @@ def submit_synthesis():
         'description': DESCRIPTION,
         "textType": "PlainText",
         'synthesisConfig': {
-            "voice": "en-US-AvaNeural",
+            "voice": "en-US-AvaMultilingualNeural",
         },
         # Replace with your custom voice name and deployment ID if you want to use custom voice.
         # Multiple voices are supported, the mixture of custom voices and platform voices is allowed.

samples/cpp/windows/console/samples/speech_synthesis_samples.cpp

@@ -114,11 +114,11 @@ void SpeechSynthesisWithVoice()
     auto config = SpeechConfig::FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
     // Sets the voice name.
-    // e.g. "en-US-AndrewNeural".
+    // e.g. "en-US-AndrewMultilingualNeural".
     // The full list of supported voices can be found here:
     // https://aka.ms/csspeech/voicenames
     // And, you can try GetVoicesAsync method to get all available voices (see SpeechSynthesisGetAvailableVoices() sample below).
-    auto voice = "en-US-AndrewNeural";
+    auto voice = "en-US-AndrewMultilingualNeural";
     config->SetSpeechSynthesisVoiceName(voice);
 
     // Creates a speech synthesizer for the specified voice, using the default speaker as audio output.
@@ -803,7 +803,7 @@ void SpeechSynthesisBookmarkEvent()
     };
 
     // Bookmark tag is needed in the SSML, e.g.
-    const auto ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>";
+    const auto ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaMultilingualNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>";
 
     cout << "Press Enter to start synthesizing." << std::endl;
     std::string text;

samples/csharp/sharedcontent/console/speech_synthesis_samples.cs

@@ -115,11 +115,11 @@ public static async Task SynthesisWithVoiceAsync()
             var config = SpeechConfig.FromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
             // Sets the voice name.
-            // e.g. "en-US-AndrewNeural".
+            // e.g. "en-US-AndrewMultilingualNeural".
             // The full list of supported voices can be found here:
             // https://aka.ms/csspeech/voicenames
             // And, you can try GetVoicesAsync method to get all available voices (see SynthesisGetAvailableVoicesAsync() sample below).
-            var voice = "en-US-AndrewNeural";
+            var voice = "en-US-AndrewMultilingualNeural";
             config.SpeechSynthesisVoiceName = voice;
 
             // Creates a speech synthesizer for the specified voice, using the default speaker as audio output.
@@ -803,7 +803,7 @@ public static async Task SynthesisBookmarkEventAsync()
                 Console.ReadLine();
 
                 // Bookmark tag is needed in the SSML, e.g.
-                var ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>";
+                var ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaMultilingualNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>";
 
                 using (var result = await synthesizer.SpeakSsmlAsync(ssml))
                 {
@@ -971,7 +971,7 @@ public static async Task SynthesizeOnceUseCustomVoiceToSpeakerAsyncSwitchPlatfor
                     || details.ErrorCode == CancellationErrorCode.ServiceTimeout
                     || details.ErrorDetails.Contains("Error code: 1007"))
                 {
-                    // Synthesize using a standard platform voice, e.g. en-US-AvaNeural
+                    // Synthesize using a standard platform voice, e.g. en-US-AvaMultilingualNeural
                     synthesisResult = await SynthesizeOnceAsyncInternal("YourSubscriptionKey", "YourServiceRegion", null, "YourPlatformVoiceName");
                 }
             }

samples/csharp/sharedcontent/console/speech_synthesis_server_scenario_sample.cs

@@ -256,7 +256,7 @@ public class SpeechSynthesisServerScenarioSample
         public static void SpeechSynthesizeWithPool()
         {
             SynthesisServer server = new SynthesisServer(subscriptionKey, region,
-                    "en-US-AvaNeural", SpeechSynthesisOutputFormat.Audio24Khz48KBitRateMonoMp3, concurrency);
+                    "en-US-AvaMultilingualNeural", SpeechSynthesisOutputFormat.Audio24Khz48KBitRateMonoMp3, concurrency);
 
             for (var turn = 0; turn < 3; turn++)
             {

samples/java/android/SpeechSynthesis/app/src/main/java/com/microsoft/cognitiveservices/speech/samples/speechsynthesis/MainActivity.java

@@ -125,7 +125,7 @@ public void onCreateSynthesizerButtonClicked(View v) {
         // Use 24k Hz format for higher quality.
         speechConfig.setSpeechSynthesisOutputFormat(SpeechSynthesisOutputFormat.Raw24Khz16BitMonoPcm);
         // Set voice name.
-        speechConfig.setSpeechSynthesisVoiceName("en-US-AvaNeural");
+        speechConfig.setSpeechSynthesisVoiceName("en-US-AvaMultilingualNeural");
         synthesizer = new SpeechSynthesizer(speechConfig, null);
         connection = Connection.fromSpeechSynthesizer(synthesizer);
 

samples/java/jre/console/src/com/microsoft/cognitiveservices/speech/samples/console/SpeechSynthesisSamples.java

@@ -126,11 +126,11 @@ public static void synthesisWithVoiceAsync() throws InterruptedException, Execut
         SpeechConfig config = SpeechConfig.fromSubscription("YourSubscriptionKey", "YourServiceRegion");
 
         // Sets the voice name.
-        // e.g. "en-US-AndrewNeural".
+        // e.g. "en-US-AndrewMultilingualNeural".
         // The full list of supported voices can be found here:
         // https://aka.ms/csspeech/voicenames
         // And, you can try getVoicesAsync method to get all available voices (see synthesisGetAvailableVoicesAsync() sample below).
-        String voice = "en-US-AndrewNeural";
+        String voice = "en-US-AndrewMultilingualNeural";
         config.setSpeechSynthesisVoiceName(voice);
 
         // Creates a speech synthesizer using the default speaker as audio output.
@@ -864,7 +864,7 @@ public static void synthesisBookmarkEventAsync() throws InterruptedException, Ex
         new Scanner(System.in).nextLine();
 
         // Bookmark tag is needed in the SSML, e.g.
-        String ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>";
+        String ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaMultilingualNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>";
 
         SpeechSynthesisResult result = synthesizer.SpeakSsmlAsync(ssml).get();
 

samples/java/jre/console/src/com/microsoft/cognitiveservices/speech/samples/console/SpeechSynthesisScenarioSamples.java

@@ -90,7 +90,7 @@ public SpeechSynthesisService() {
         /**
          * A thread-safe method to synthesize content
          * @param content The text to synthesize
-         * @param voice The voice name, e.g. en-US-AvaNeural
+         * @param voice The voice name, e.g. en-US-AvaMultilingualNeural
          * @return The first byte latency and processing time, in millisecond.
          */
         public long[] synthesis(String content, String voice) {
@@ -149,7 +149,7 @@ public static void synthesisServerScenarioAsync() throws InterruptedException {
             System.out.printf("Turn: %d%n", finalTurn);
 
             IntStream.range(0, 64).parallel().forEach(i -> {
-                long[] latency = service.synthesis(String.format("today is a nice day. %d%d", finalTurn, i), "en-US-AvaNeural");
+                long[] latency = service.synthesis(String.format("today is a nice day. %d%d", finalTurn, i), "en-US-AvaMultilingualNeural");
                 if (finalTurn > 0) {
                     latencies.add(latency[0]);
                     processingTimes.add(latency[1]);

samples/js/browser/index.html

@@ -143,7 +143,7 @@ <h3 style="font-weight:500;">Javascript Browser Sample</h3>
                         <option value="en-CA-ClaraNeural">English - CA</option>
                         <option value="en-GB-NoahNeural">English - GB</option>
                         <option value="en-IN-NeerjaNeural">English - IN</option>
-                        <option value="en-US-AvaNeural">English - US</option>
+                        <option value="en-US-AvaMultilingualNeural">English - US</option>
                         <option value="es-ES-ElviraNeural">Spanish - ES</option>
                         <option value="es-MX-LibertoNeural">Spanish - MX</option>
                         <option value="fi-FI-HarriNeural">Finnish - FI</option>

samples/js/browser/public/index.html

@@ -147,7 +147,7 @@ <h3 style="font-weight:500;">Javascript Browser Sample</h3>
                         <option value="en-CA-ClaraNeural">English - CA</option>
                         <option value="en-GB-NoahNeural">English - GB</option>
                         <option value="en-IN-NeerjaNeural">English - IN</option>
-                        <option value="en-US-AvaNeural">English - US</option>
+                        <option value="en-US-AvaMultilingualNeural">English - US</option>
                         <option value="es-ES-ElviraNeural">Spanish - ES</option>
                         <option value="es-MX-LibertoNeural">Spanish - MX</option>
                         <option value="fi-FI-HarriNeural">Finnish - FI</option>

samples/js/browser/public/synthesis.html

@@ -317,7 +317,7 @@ <h1 style="font-weight:500;">Speech Speech SDK not found
         request.onload = function() {
           if (request.status >= 200 && request.status < 400) {
             const response = this.response;
-            const defaultVoice = "AndrewNeural";
+            const defaultVoice = "AndrewMultilingualNeural";
             let selectId;
             const data = JSON.parse(response);
             voiceOptions.innerHTML = "";

samples/js/browser/synthesis.html

@@ -313,7 +313,7 @@ <h1 style="font-weight:500;">Speech Speech SDK not found
         request.onload = function() {
           if (request.status >= 200 && request.status < 400) {
             const response = this.response;
-            const defaultVoice = "AndrewNeural";
+            const defaultVoice = "AndrewMultilingualNeural";
             let selectId;
             const data = JSON.parse(response);
             voiceOptions.innerHTML = "";

samples/js/node/synthesis.js

@@ -15,7 +15,7 @@ export const main = (settings, filename) => {
     // setting the synthesis language, voice name, and output audio format.
     // see https://aka.ms/speech/tts-languages for available languages and voices
     speechConfig.speechSynthesisLanguage = settings.language;
-    speechConfig.speechSynthesisVoiceName = "en-US-AvaNeural";
+    speechConfig.speechSynthesisVoiceName = "en-US-AvaMultilingualNeural";
     speechConfig.speechSynthesisOutputFormat = sdk.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3;
 
     var rl = readline.createInterface({

samples/kotlin/android/tts-pause-example/app/src/main/java/com/microsoft/cognitiveservices/speech/samples/speechsynthesis/pauseexample/MainActivity.kt

@@ -109,7 +109,7 @@ class MainActivity : AppCompatActivity() {
         // Use 24k Hz format for higher quality.
         speechConfig?.setSpeechSynthesisOutputFormat(SpeechSynthesisOutputFormat.Raw24Khz16BitMonoPcm)
         // Set voice name.
-        speechConfig?.speechSynthesisVoiceName = "en-US-AvaNeural"
+        speechConfig?.speechSynthesisVoiceName = "en-US-AvaMultilingualNeural"
         synthesizer = SpeechSynthesizer(speechConfig, null)
         connection = Connection.fromSpeechSynthesizer(synthesizer)
 

samples/objective-c/ios/synthesis-samples/synthesis-samples/ViewController.m

@@ -452,7 +452,7 @@ - (void)synthesisEvent {
         }];
 
         // To trigger a bookmark event, bookmark tags are required in the SSML, e.g.
-        // "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>"
+        // "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='http://www.w3.org/2001/mstts'><voice name='en-US-AvaMultilingualNeural'><bookmark mark='bookmark_one'/> one. <bookmark mark='bookmark_two'/> two. three. four.</voice></speak>"
         [synthesizerForEvents addBookmarkReachedEventHandler: ^ (SPXSpeechSynthesizer *synthesizer, SPXSpeechSynthesisBookmarkEventArgs *eventArgs) {
             // The unit of AudioOffset is tick (1 tick = 100 nanoseconds), divide by 10,000 to converted to milliseconds.
             NSLog(@"Bookmark reached. Audio offset: %fms, bookmark text: %@.", eventArgs.audioOffset/10000., eventArgs.text);

samples/python/console/long-form-text-synthesis/long_form_text_synthesis.py

@@ -28,7 +28,7 @@
 
 class LongTextSynthesizer:
     def __init__(self, subscription: str, region: str, language: str = 'english',
-                 voice: str = 'en-US-AvaNeural', parallel_threads: int = 8) -> None:
+                 voice: str = 'en-US-AvaMultilingualNeural', parallel_threads: int = 8) -> None:
         self.is_ssml = None
         self.subscription = subscription
         self.region = region

samples/python/console/speech_synthesis_sample.py

@@ -87,12 +87,12 @@ def speech_synthesis_with_voice():
     # Creates an instance of a speech config with specified subscription key and service region.
     speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
     # Sets the synthesis voice name.
-    # e.g. "en-US-AndrewNeural".
+    # e.g. "en-US-AndrewMultilingualNeural".
     # The full list of supported voices can be found here:
     # https://aka.ms/csspeech/voicenames
     # And, you can try get_voices_async method to get all available voices.
     # See speech_synthesis_get_available_voices() sample below.
-    voice = "en-US-AndrewNeural"
+    voice = "en-US-AndrewMultilingualNeural"
     speech_config.speech_synthesis_voice_name = voice
     # Creates a speech synthesizer for the specified voice,
     # using the default speaker as audio output.
@@ -522,7 +522,7 @@ def speech_synthesis_bookmark_event():
     # Bookmark tag is needed in the SSML, e.g.
     ssml = "<speak version='1.0' xml:lang='en-US' xmlns='http://www.w3.org/2001/10/synthesis' " \
            "xmlns:mstts='http://www.w3.org/2001/mstts'>" \
-           "<voice name='en-US-AvaNeural'>" \
+           "<voice name='en-US-AvaMultilingualNeural'>" \
            "<bookmark mark='bookmark_one'/> one. " \
            "<bookmark mark='bookmark_two'/> two. three. four.</voice></speak> "