Get facial position with viseme

using (var synthesizer = new SpeechSynthesizer(speechConfig, audioConfig))
{
    // Subscribes to viseme received event
    synthesizer.VisemeReceived += (s, e) =>
    {
        Console.WriteLine($"Viseme event received. Audio offset: " +
            $"{e.AudioOffset / 10000}ms, viseme id: {e.VisemeId}.");

        // `Animation` is an xml string for SVG or a json string for blend shapes
        var animation = e.Animation;
    };

    // If VisemeID is the only thing you want, you can also use `SpeakTextAsync()`
    var result = await synthesizer.SpeakSsmlAsync(ssml);
}

auto synthesizer = SpeechSynthesizer::FromConfig(speechConfig, audioConfig);

// Subscribes to viseme received event
synthesizer->VisemeReceived += [](const SpeechSynthesisVisemeEventArgs& e)
{
    cout << "viseme event received. "
        // The unit of e.AudioOffset is tick (1 tick = 100 nanoseconds), divide by 10,000 to convert to milliseconds.
        << "Audio offset: " << e.AudioOffset / 10000 << "ms, "
        << "viseme id: " << e.VisemeId << "." << endl;

    // `Animation` is an xml string for SVG or a json string for blend shapes
    auto animation = e.Animation;
};

// If VisemeID is the only thing you want, you can also use `SpeakTextAsync()`
auto result = synthesizer->SpeakSsmlAsync(ssml).get();

SpeechSynthesizer synthesizer = new SpeechSynthesizer(speechConfig, audioConfig);

// Subscribes to viseme received event
synthesizer.VisemeReceived.addEventListener((o, e) -> {
    // The unit of e.AudioOffset is tick (1 tick = 100 nanoseconds), divide by 10,000 to convert to milliseconds.
    System.out.print("Viseme event received. Audio offset: " + e.getAudioOffset() / 10000 + "ms, ");
    System.out.println("viseme id: " + e.getVisemeId() + ".");

    // `Animation` is an xml string for SVG or a json string for blend shapes
    String animation = e.getAnimation();
});

// If VisemeID is the only thing you want, you can also use `SpeakTextAsync()`
SpeechSynthesisResult result = synthesizer.SpeakSsmlAsync(ssml).get();

speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=audio_config)

def viseme_cb(evt):
    print("Viseme event received: audio offset: {}ms, viseme id: {}.".format(
        evt.audio_offset / 10000, evt.viseme_id))

    # `Animation` is an xml string for SVG or a json string for blend shapes
    animation = evt.animation

# Subscribes to viseme received event
speech_synthesizer.viseme_received.connect(viseme_cb)

# If VisemeID is the only thing you want, you can also use `speak_text_async()`
result = speech_synthesizer.speak_ssml_async(ssml).get()

var synthesizer = new SpeechSDK.SpeechSynthesizer(speechConfig, audioConfig);

// Subscribes to viseme received event
synthesizer.visemeReceived = function (s, e) {
    window.console.log("(Viseme), Audio offset: " + e.audioOffset / 10000 + "ms. Viseme ID: " + e.visemeId);

    // `Animation` is an xml string for SVG or a json string for blend shapes
    var animation = e.animation;
}

// If VisemeID is the only thing you want, you can also use `speakTextAsync()`
synthesizer.speakSsmlAsync(ssml);

SPXSpeechSynthesizer *synthesizer =
    [[SPXSpeechSynthesizer alloc] initWithSpeechConfiguration:speechConfig
                                           audioConfiguration:audioConfig];

// Subscribes to viseme received event
[synthesizer addVisemeReceivedEventHandler: ^ (SPXSpeechSynthesizer *synthesizer, SPXSpeechSynthesisVisemeEventArgs *eventArgs) {
    NSLog(@"Viseme event received. Audio offset: %fms, viseme id: %lu.", eventArgs.audioOffset/10000., eventArgs.visemeId);

    // `Animation` is an xml string for SVG or a json string for blend shapes
    NSString *animation = eventArgs.Animation;
}];

// If VisemeID is the only thing you want, you can also use `SpeakText`
[synthesizer speakSsml:ssml];