How to use microsoft-cognitiveservices-speech-sdk - 10 common examples

To help you get started, we’ve selected a few microsoft-cognitiveservices-speech-sdk examples, based on popular ways it is used in public projects.

github Azure-Samples / cognitive-services-speech-sdk / quickstart / js-node / index.js View on Github external
// create the push stream we need for the speech sdk.
  var pushStream = sdk.AudioInputStream.createPushStream();
  
  // open the file and push it to the push stream.
  fs.createReadStream(filename).on('data', function(arrayBuffer) {
    pushStream.write(arrayBuffer.slice());
  }).on('end', function() {
    pushStream.close();
  });
  
  // we are done with the setup
  console.log("Now recognizing from: " + filename);
  
  // now create the audio-config pointing to our stream and
  // the speech config specifying the language.
  var audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
  var speechConfig = sdk.SpeechConfig.fromSubscription(subscriptionKey, serviceRegion);
  
  // setting the recognition language to English.
  speechConfig.speechRecognitionLanguage = "en-US";
  
  // create the speech recognizer.
  var recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);
  
  // start the recognizer and wait for a result.
  recognizer.recognizeOnceAsync(
    function (result) {
      console.log(result);
  
      recognizer.close();
      recognizer = undefined;
    },
github Azure-Samples / cognitive-services-speech-sdk / quickstart / js-node / index.js View on Github external
  "use strict";
  
  // pull in the required packages.
  var sdk = require("microsoft-cognitiveservices-speech-sdk");
  var fs = require("fs");
  
  // replace with your own subscription key,
  // service region (e.g., "westus"), and
  // the name of the file you want to run
  // through the speech recognizer.
  var subscriptionKey = "YourSubscriptionKey";
  var serviceRegion = "YourServiceRegion"; // e.g., "westus"
  var filename = "YourAudioFile.wav"; // 16000 Hz, Mono
  
  // create the push stream we need for the speech sdk.
  var pushStream = sdk.AudioInputStream.createPushStream();
  
  // open the file and push it to the push stream.
  fs.createReadStream(filename).on('data', function(arrayBuffer) {
    pushStream.write(arrayBuffer.slice());
  }).on('end', function() {
    pushStream.close();
  });
  
  // we are done with the setup
  console.log("Now recognizing from: " + filename);
  
  // now create the audio-config pointing to our stream and
  // the speech config specifying the language.
  var audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
  var speechConfig = sdk.SpeechConfig.fromSubscription(subscriptionKey, serviceRegion);
github Azure-Samples / cognitive-services-speech-sdk / quickstart / js-node / index.js View on Github external
var pushStream = sdk.AudioInputStream.createPushStream();
  
  // open the file and push it to the push stream.
  fs.createReadStream(filename).on('data', function(arrayBuffer) {
    pushStream.write(arrayBuffer.slice());
  }).on('end', function() {
    pushStream.close();
  });
  
  // we are done with the setup
  console.log("Now recognizing from: " + filename);
  
  // now create the audio-config pointing to our stream and
  // the speech config specifying the language.
  var audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
  var speechConfig = sdk.SpeechConfig.fromSubscription(subscriptionKey, serviceRegion);
  
  // setting the recognition language to English.
  speechConfig.speechRecognitionLanguage = "en-US";
  
  // create the speech recognizer.
  var recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);
  
  // start the recognizer and wait for a result.
  recognizer.recognizeOnceAsync(
    function (result) {
      console.log(result);
  
      recognizer.close();
      recognizer = undefined;
    },
    function (err) {
github Azure-Samples / cognitive-services-speech-sdk / quickstart / js-node / index.js View on Github external
pushStream.close();
  });
  
  // we are done with the setup
  console.log("Now recognizing from: " + filename);
  
  // now create the audio-config pointing to our stream and
  // the speech config specifying the language.
  var audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
  var speechConfig = sdk.SpeechConfig.fromSubscription(subscriptionKey, serviceRegion);
  
  // setting the recognition language to English.
  speechConfig.speechRecognitionLanguage = "en-US";
  
  // create the speech recognizer.
  var recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);
  
  // start the recognizer and wait for a result.
  recognizer.recognizeOnceAsync(
    function (result) {
      console.log(result);
  
      recognizer.close();
      recognizer = undefined;
    },
    function (err) {
      console.trace("err - " + err);
  
      recognizer.close();
      recognizer = undefined;
    });
  // </code>
github microsoft / BotFramework-WebChat / packages / directlinespeech / src / createAdapters.js View on Github external
if (textNormalization) {
    console.warn(
      'botframework-directlinespeech: Text normalization is currently not supported; ignoring "textNormalization".'
    );
  }

  if (userID || username) {
    console.warn(
      'botframework-directlinespeech: Custom "userId" and "username" are currently not supported and are ignored.'
    );
  }

  let config;

  if (authorizationToken) {
    config = BotFrameworkConfig.fromAuthorizationToken(authorizationToken, region);
  } else {
    config = BotFrameworkConfig.fromSubscription(subscriptionKey, region);
  }

  // Supported options can be found in DialogConnectorFactory.js.

  // Set the language used for recognition.
  config.setProperty(PropertyId.SpeechServiceConnection_RecoLanguage, speechRecognitionLanguage);

  // The following code sets the output format.
  // As advised by the Speech team, this API may be subject to future changes.
  // We are not enabling output format option because it does not send detailed output format to the bot, rendering this option useless.
  // config.setProperty(PropertyId.SpeechServiceResponse_OutputFormatOption, OutputFormat[OutputFormat.Detailed]);

  // Set the user ID for starting the conversation.
  userID && config.setProperty(PropertyId.Conversation_From_Id, userID);
github microsoft / BotFramework-WebChat / packages / directlinespeech / src / createAdapters.js View on Github external
'botframework-directlinespeech: Text normalization is currently not supported; ignoring "textNormalization".'
    );
  }

  if (userID || username) {
    console.warn(
      'botframework-directlinespeech: Custom "userId" and "username" are currently not supported and are ignored.'
    );
  }

  let config;

  if (authorizationToken) {
    config = BotFrameworkConfig.fromAuthorizationToken(authorizationToken, region);
  } else {
    config = BotFrameworkConfig.fromSubscription(subscriptionKey, region);
  }

  // Supported options can be found in DialogConnectorFactory.js.

  // Set the language used for recognition.
  config.setProperty(PropertyId.SpeechServiceConnection_RecoLanguage, speechRecognitionLanguage);

  // The following code sets the output format.
  // As advised by the Speech team, this API may be subject to future changes.
  // We are not enabling output format option because it does not send detailed output format to the bot, rendering this option useless.
  // config.setProperty(PropertyId.SpeechServiceResponse_OutputFormatOption, OutputFormat[OutputFormat.Detailed]);

  // Set the user ID for starting the conversation.
  userID && config.setProperty(PropertyId.Conversation_From_Id, userID);

  // Set Custom Speech and Custom Voice.
github Azure-Samples / cognitive-services-speech-sdk / samples / js / node / synthesis.js View on Github external
var audioConfig = sdk.AudioConfig.fromAudioFileOutput(filename);
        var speechConfig = sdk.SpeechConfig.fromSubscription(settings.subscriptionKey, settings.serviceRegion);

        // 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-AriaRUS";
        speechConfig.speechSynthesisOutputFormat = sdk.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3;

        var rl = readline.createInterface({
            input: process.stdin,
            output: process.stdout
        });

        // create the speech synthesizer.
        var synthesizer = new sdk.SpeechSynthesizer(speechConfig, audioConfig);

        // Before beginning speech synthesis, setup the callbacks to be invoked when an event occurs.

        // The event synthesizing signals that a synthesized audio chunk is received.
        // You will receive one or more synthesizing events as a speech phrase is synthesized.
        // You can use this callback to streaming receive the synthesized audio.
        synthesizer.synthesizing = function (s, e) {
            var str = "(synthesizing) Reason: " + sdk.ResultReason[e.result.reason] + " Audio chunk length: " + e.result.audioData.byteLength;
            console.log(str);
        };

        // The event synthesis completed signals that the synthesis is completed.
        synthesizer.synthesisCompleted = function (s, e) {
            console.log("(synthesized)  Reason: " + sdk.ResultReason[e.result.reason] + " Audio length: " + e.result.audioData.byteLength);
        };
github Azure-Samples / cognitive-services-speech-sdk / samples / js / node / synthesis.js View on Github external
main: function(settings, filename) {

        // now create the audio-config pointing to the output file.
        // You can also use audio output stream to initialize the audio config, see the docs for details.
        var audioConfig = sdk.AudioConfig.fromAudioFileOutput(filename);
        var speechConfig = sdk.SpeechConfig.fromSubscription(settings.subscriptionKey, settings.serviceRegion);

        // 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-AriaRUS";
        speechConfig.speechSynthesisOutputFormat = sdk.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3;

        var rl = readline.createInterface({
            input: process.stdin,
            output: process.stdout
        });

        // create the speech synthesizer.
        var synthesizer = new sdk.SpeechSynthesizer(speechConfig, audioConfig);
github Azure-Samples / cognitive-services-speech-sdk / samples / js / node / index.js View on Github external
function openPushStream(filename) {
        // create the push stream we need for the speech sdk.
        var pushStream = sdk.AudioInputStream.createPushStream();
    
        // open the file and push it to the push stream.
        fs.createReadStream(filename).on('data', function(arrayBuffer) {
            pushStream.write(arrayBuffer.slice());
        }).on('end', function() {
            pushStream.close();
        });
    
        return pushStream;
    }
github Azure-Samples / cognitive-services-speech-sdk / samples / js / node / synthesis.js View on Github external
main: function(settings, filename) {

        // now create the audio-config pointing to the output file.
        // You can also use audio output stream to initialize the audio config, see the docs for details.
        var audioConfig = sdk.AudioConfig.fromAudioFileOutput(filename);
        var speechConfig = sdk.SpeechConfig.fromSubscription(settings.subscriptionKey, settings.serviceRegion);

        // 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-AriaRUS";
        speechConfig.speechSynthesisOutputFormat = sdk.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3;

        var rl = readline.createInterface({
            input: process.stdin,
            output: process.stdout
        });

        // create the speech synthesizer.
        var synthesizer = new sdk.SpeechSynthesizer(speechConfig, audioConfig);

        // Before beginning speech synthesis, setup the callbacks to be invoked when an event occurs.