/// <summary>
/// Reads the specified phrase, with the default text-to-speech voice.
/// </summary>
/// <param name="phrase">The text to say.</param>
/// <param name="media">The <see cref="MediaElement"/> that plays the speech.</param>
/// <remarks><para>This method is awaitable, because in the case of a speech prompt,
/// the speech recognizer can hear the prompt and may process it, along with
/// the user's speech. Avoid this bug by awaiting the call to the <see cref="SpeakAsync"/> method
/// and then setting <see cref="RecognitionMode"/> to <see cref="SpeechRecognitionMode.Dictation"/>
/// after it completes. This way, the speech prompt ends before recognition begins.</para>
/// <para>Also, the <see cref="SpeakAsync"/> method stops the current recognition session,
/// so the user and any spoken prompts don't trigger speech commands.</para>
/// <para>The <see cref="SpeakAsync"/> method uses the <see cref="SemaphoreSlim"/> class to implement
/// a signal from the <see cref="MediaElement.MediaEnded"/> event handler to this method.
/// </para>
/// </remarks>
public async Task SpeakAsync(string phrase, MediaElement media)
{
if (!String.IsNullOrEmpty(phrase))
{
// Turn off speech recognition while speech synthesis is happening.
await SetRecognitionMode(SpeechRecognitionMode.Paused);
MediaPlayerElement = media;
SpeechSynthesisStream synthesisStream = await SpeechSynth.SynthesizeTextToStreamAsync(phrase);
// The Play call starts the sound stream playback and immediately returns,
// so a semaphore is required to make the SpeakAsync method awaitable.
media.AutoPlay = true;
media.SetSource(synthesisStream, synthesisStream.ContentType);
media.Play();
// Wait until the MediaEnded event on MediaElement is raised,
// before turning on speech recognition again. The semaphore
// is signaled in the mediaElement_MediaEnded event handler.
await Semaphore.WaitAsync();
// Turn on speech recognition and listen for commands.
await SetRecognitionMode(SpeechRecognitionMode.CommandPhrases);
}
}
public void TestMethod1()
{
string startupText = "Welcome to the speech synthesizer. Please enter text and press enter to hear me speak what you write:";
SpeechSynth.Main();
Assert.AreEqual(Console.Out.ToString(), startupText);
Environment.Exit(0);
}
public async Task <bool> Test1()
{
using (var _synth = new SpeechSynth())
{
var m = //"That'd be just amazing!";//
"Привет. Можно ли чаю? Can I have a cup of tea?"; // "Is this awesome or what!";
//"Привет. Awesome! Awesome? Are you OK?";
//"Hi there. Hi there! Hi there?";
var voices = _voicenames
.Where(v => v.EndsWith("RUS"))
//.Where(v => v.EndsWith("ural"))
//.Where(v => v.StartsWith("zh-CN-Xia"))
//.Where(v => v.StartsWith("en-A"))
//.Where(v => v.StartsWith("ru-"))
.ToArray();
var speakingStyles = new[] { // https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-synthesis-markup?tabs=csharp#adjust-speaking-styles
"angry", // XiaoxiaoNeural only
//"sad" , // XiaoxiaoNeural only
//"affectionate", // XiaoxiaoNeural only
//"newscast-formal" , // AriaNeural only
//"newscast-casual" , // AriaNeural only
//"customerservice" , // AriaNeural only
//"chat" , // AriaNeural only
//"cheerful" , // AriaNeural only
//"empathetic" // AriaNeural only
};
Console.WriteLine($"v-{voices.Length} x {speakingStyles.Length} styles = ");
for (var v = 0; v < voices.Length; v++)
{
for (var s = 0; s < speakingStyles.Length; s++)
{
//await _synth.SpeakAsync(m, VMode.Prosody, voices[v], speakingStyle: speakingStyles[s]);
await sayIt(_synth, m, voices, speakingStyles, s, v);
}
}
//await _synth.SpeakAsync(s, a, "ru-RU-Irina");
//await _synth.SpeakAsync(s, a, "ru-RU-Pavel");
//await _synth.SpeakAsync(s, a, "ru-RU-EkaterinaRUS");
//await _synth.SpeakAsync(s, a, "ru-RU-DariyaNeural"); // bad ending
//await _synth.SpeakAsync(s, a, "ru-RU-SvetlanaNeural"); // the best
//await _synth.SpeakAsync(s, a, "ru-RU-DmitryNeural"); // best question intonation
}
return(true);
}
// Define the event handlers.
private void OnChanged(object source, FileSystemEventArgs e)
{
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
var output = speechRecogniser.GetTopResult(e.FullPath);
Console.WriteLine("RecognisedSpeech:" + stopwatch.ElapsedMilliseconds.ToString() + "ms");
Console.WriteLine(output);
stopwatch.Restart();
var response = responder.GetResponse(output);
Console.WriteLine("Responder:" + stopwatch.ElapsedMilliseconds.ToString() + "ms");
stopwatch.Restart();
SpeechSynth.SynthesisToSpeakerAsync(response).Wait();
Console.WriteLine("SpeechSynthesiser:" + stopwatch.ElapsedMilliseconds.ToString() + "ms");
File.Delete(e.FullPath);
}
private void Say()
{
var t = ddlSay.Text;
if (!string.IsNullOrEmpty(t))
{
SpeechSynth.Say(t, CW);
CW.LogToPlugin("Text: " + t);
var p = new List <string> {
t
};
foreach (var i in ddlSay.Items)
{
if (!p.Contains(i) && !string.IsNullOrEmpty(i.ToString()))
{
p.Add(i.ToString());
}
}
var x = "";
int j = 0;
foreach (string s in p)
{
if (j < 10)
{
x += s + "|";
}
else
{
break;
}
j++;
}
x = x.Trim('|');
MainForm.Conf.TextSentences = x;
PopSentences();
}
}
static async Task sayIt(SpeechSynth _synth, string m, string[] voices, string[] speakingStyles, int s, int v)
{
Console.WriteLine($" --- {m}, VMode.Express, {voices[v],-26} {speakingStyles[s],-16}");
await _synth.SpeakAsync(m, VMode.Express, voice : voices[v], styleForExpressOnly : speakingStyles[s]);
}
