public async Task <string> SynthesisToSpeakerAsync(string text)
{
var config = GetClient();
var sb = new StringBuilder();
using var synthesizer = new SpeechSynthesizer(config,
AutoDetectSourceLanguageConfig.FromOpenRange(),
AudioConfig.FromDefaultSpeakerOutput());
using var result = await synthesizer.SpeakTextAsync(text);
if (result.Reason == ResultReason.SynthesizingAudioCompleted)
{
sb.AppendLine($"Speech synthesized to speaker for text [{text}]");
}
else if (result.Reason == ResultReason.Canceled)
{
var cancellation = SpeechSynthesisCancellationDetails.FromResult(result);
sb.AppendLine($"CANCELED: Reason={cancellation.Reason}");
if (cancellation.Reason == CancellationReason.Error)
{
sb.AppendLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
sb.AppendLine($"CANCELED: ErrorDetails=[{cancellation.ErrorDetails}]");
sb.AppendLine($"CANCELED: Did you update the subscription info?");
}
}
return(sb.ToString());
}
// Speech synthesis with auto detection for source language
// Note: this is a preview feature, which might be updated in future versions.
public static async Task SynthesisWithAutoDetectSourceLanguageAsync()
{
// Creates an instance of a speech config with specified subscription key and service region.
// Replace with your own subscription key and service region (e.g., "westus").
// The default language is "en-us".
var config = SpeechConfig.FromSubscription("YourSubscriptionKey", "YourServiceRegion");
// Creates an instance of AutoDetectSourceLanguageConfig with open languages range
var autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig.FromOpenRange();
// Creates a speech synthesizer with auto detection for source language, using the default speaker as audio output.
using (var synthesizer = new SpeechSynthesizer(config, autoDetectSourceLanguageConfig,
AudioConfig.FromDefaultSpeakerOutput()))
{
while (true)
{
// Receives a multi lingual text from console input and synthesize it to speaker.
// For example, you can input "Bonjour le monde. Hello world.", then you will hear "Bonjour le monde."
// spoken in a French voice and "Hello world." in an English voice.
Console.WriteLine("Enter some text that you want to speak, or enter empty text to exit.");
Console.Write("> ");
string text = Console.ReadLine();
if (string.IsNullOrEmpty(text))
{
break;
}
using (var result = await synthesizer.SpeakTextAsync(text))
{
if (result.Reason == ResultReason.SynthesizingAudioCompleted)
{
Console.WriteLine($"Speech synthesized to speaker for text [{text}]");
}
else if (result.Reason == ResultReason.Canceled)
{
var cancellation = SpeechSynthesisCancellationDetails.FromResult(result);
Console.WriteLine($"CANCELED: Reason={cancellation.Reason}");
if (cancellation.Reason == CancellationReason.Error)
{
Console.WriteLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
Console.WriteLine($"CANCELED: ErrorDetails=[{cancellation.ErrorDetails}]");
Console.WriteLine($"CANCELED: Did you update the subscription info?");
}
}
}
}
}
}
public static async Task RecognizeLng()
{
SpeechConfig speechConfig = SpeechConfig.FromEndpoint(new System.Uri(ConfigurationManager.AppSettings.Get("SpeechEndpoint")), ConfigurationManager.AppSettings.Get("TTSKey"));
AudioConfig audioConfig = AudioConfig.FromDefaultSpeakerOutput();
AutoDetectSourceLanguageConfig autoDetectSourceLanguageConfig = AutoDetectSourceLanguageConfig
.FromLanguages(new string[] { "en-US", "ru-RU" });
using (var recognizer = new SpeechRecognizer(
speechConfig,
autoDetectSourceLanguageConfig,
audioConfig))
{
Console.WriteLine("Say something...");
var speechRecognitionResult = await recognizer.RecognizeOnceAsync();
var autoDetectSourceLanguageResult =
AutoDetectSourceLanguageResult.FromResult(speechRecognitionResult);
var detectedLng = autoDetectSourceLanguageResult.Language;
Console.WriteLine("I recognized " + speechRecognitionResult.Text + " in " + detectedLng);
}
}
async Task <byte[]> SynthesizeAudioAsync(string msg)
{
var response = new byte[] { };
var autoDetecConfig = AutoDetectSourceLanguageConfig.FromOpenRange();
using var synthesizer = new SpeechSynthesizer(_speechConfig, autoDetecConfig, AudioConfig.FromDefaultSpeakerOutput());
using var result = await synthesizer.SpeakTextAsync(msg);
if (result.Reason == ResultReason.SynthesizingAudioCompleted)
{
response = result.AudioData;
}
return(response);
}
// https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-recognize-speech-csharp
public void Start(string culture, Action <string> recognized, string wakeupKeyword = default, int awakeTimeout = 6000, Action <bool> awakeningHandler = default, Action <string> recognizing = default)
{
this.wakeupKeyword = wakeupKeyword;
this.awakeTimeout = awakeTimeout;
this.awakeningHandler = awakeningHandler;
var audioInput = AudioConfig.FromDefaultMicrophoneInput();
var speechInputConfig = SpeechConfig.FromSubscription(config["SpeechToText.SubscriptionKey"], config["SpeechToText.SpeechRegion"]);
speechInputConfig.OutputFormat = OutputFormat.Detailed;
speechInputConfig.SpeechRecognitionLanguage = culture;
recognizer = new SpeechRecognizer(speechInputConfig, audioInput);
recognizer.Recognizing += (s, e) =>
{
isRecognizing = true;
if (recognizing == default)
{
return;
}
var text = e.Result.Text.Clean();
if (text.IsEmpty())
{
return;
}
recognizing(text);
};
recognizer.Recognized += (s, e) => {
isRecognizing = false;
if (e.Result.Reason != ResultReason.RecognizedSpeech)
{
return;
}
var text = e.Result.Text.Clean();
if (text.IsEmpty())
{
return;
}
if (this.awakening != null)
{
recognized(text);
WakeDown();
}
else
{
var wakeupKeywordIndex = text.IndexOf(wakeupKeyword, 0, StringComparison.InvariantCultureIgnoreCase);
if (wakeupKeywordIndex < 0)
{
return;
}
var beforeText = string.Empty;
if (wakeupKeywordIndex > 0)
{
beforeText = text.Substring(0, wakeupKeywordIndex - 1).Clean();
}
var afterText = text.Substring(wakeupKeywordIndex + wakeupKeyword.Length).Clean();
if (afterText.IsEmpty())
{
if (beforeText.IsEmpty())
{
WakeUp();
}
else
{
recognized(beforeText);
}
}
else if (beforeText.IsEmpty())
{
recognized(afterText);
}
else
{
recognized($"{beforeText} {afterText}");
}
}
};
recognizer.StartContinuousRecognitionAsync().Wait();
var audioOutput = AudioConfig.FromDefaultSpeakerOutput();
var speechOutputConfig = SpeechConfig.FromSubscription(config["SpeechToText.SubscriptionKey"], config["SpeechToText.SpeechRegion"]);
speechOutputConfig.SpeechSynthesisLanguage = culture;
speechOutputConfig.SpeechSynthesisVoiceName = config[$"TextToSpeech.VoiceName.{culture}"];
syntetizer = new SpeechSynthesizer(speechOutputConfig, audioOutput);
}