How to integrate Azure Voice API in node.js

Question

Now I am integrating Azure Voice API in my MERN stack project. I tested it in console with debugging but it doesn't work on React Website.

I am not sure what's the problem.

Answer 1

It's the way I found.

const fs = require('fs');
const sdk = require("microsoft-cognitiveservices-speech-sdk");
const speechConfig = sdk.SpeechConfig.fromSubscription("<paste-your-speech-key-here>", "<paste-your-speech-location/region-here>");

function fromStream() {
    let pushStream = sdk.AudioInputStream.createPushStream();

    fs.createReadStream("YourAudioFile.wav").on('data', function(arrayBuffer) {
        pushStream.write(arrayBuffer.slice());
    }).on('end', function() {
        pushStream.close();
    });
 
    let audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
    let recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);
    recognizer.recognizeOnceAsync(result => {
        console.log(`RECOGNIZED: Text=${result.text}`);
        recognizer.close();
    });
}
fromStream();

Answer 2

Install the Speech SDK

const sdk = require("microsoft-cognitiveservices-speech-sdk");

Create a speech configuration

const speechConfig = sdk.SpeechConfig.fromSubscription("<paste-your-speech-key-here>", "<paste-your-speech-location/region-here>");

There are a few other ways that you can initialize a SpeechConfig

Recognize from file

const fs = require('fs');
const sdk = require("microsoft-cognitiveservices-speech-sdk");
const speechConfig = sdk.SpeechConfig.fromSubscription("<paste-your-speech-key-here>", "<paste-your-speech-location/region-here>");

function fromFile() {
    let audioConfig = sdk.AudioConfig.fromWavFileInput(fs.readFileSync("YourAudioFile.wav"));
    let recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);

    recognizer.recognizeOnceAsync(result => {
        console.log(`RECOGNIZED: Text=${result.text}`);
        recognizer.close();
    });
}
fromFile();

Recognize from in-memory stream

const fs = require('fs');
const sdk = require("microsoft-cognitiveservices-speech-sdk");
const speechConfig = sdk.SpeechConfig.fromSubscription("<paste-your-speech-key-here>", "<paste-your-speech-location/region-here>");

function fromStream() {
    let pushStream = sdk.AudioInputStream.createPushStream();

    fs.createReadStream("YourAudioFile.wav").on('data', function(arrayBuffer) {
        pushStream.write(arrayBuffer.slice());
    }).on('end', function() {
        pushStream.close();
    });
 
    let audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
    let recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);
    recognizer.recognizeOnceAsync(result => {
        console.log(`RECOGNIZED: Text=${result.text}`);
        recognizer.close();
    });
}
fromStream();

Error handling

switch (result.reason) {
    case sdk.ResultReason.RecognizedSpeech:
        console.log(`RECOGNIZED: Text=${result.text}`);
        break;
    case sdk.ResultReason.NoMatch:
        console.log("NOMATCH: Speech could not be recognized.");
        break;
    case sdk.ResultReason.Canceled:
        const cancellation = CancellationDetails.fromResult(result);
        console.log(`CANCELED: Reason=${cancellation.reason}`);

        if (cancellation.reason == sdk.CancellationReason.Error) {
            console.log(`CANCELED: ErrorCode=${cancellation.ErrorCode}`);
            console.log(`CANCELED: ErrorDetails=${cancellation.errorDetails}`);
            console.log("CANCELED: Did you update the key and location/region info?");
        }
        break;
    }

Continuous recognition

Start by defining the input and initializing a SpeechRecognizer :

const recognizer = new sdk.SpeechRecognizer(speechConfig, audioConfig);

Next, subscribe to the events sent from the SpeechRecognizer .

recognizer.recognizing = (s, e) => {
    console.log(`RECOGNIZING: Text=${e.result.text}`);
};

recognizer.recognized = (s, e) => {
    if (e.result.reason == sdk.ResultReason.RecognizedSpeech) {
        console.log(`RECOGNIZED: Text=${e.result.text}`);
    }
    else if (e.result.reason == sdk.ResultReason.NoMatch) {
        console.log("NOMATCH: Speech could not be recognized.");
    }
};

recognizer.canceled = (s, e) => {
    console.log(`CANCELED: Reason=${e.reason}`);

    if (e.reason == sdk.CancellationReason.Error) {
        console.log(`"CANCELED: ErrorCode=${e.errorCode}`);
        console.log(`"CANCELED: ErrorDetails=${e.errorDetails}`);
        console.log("CANCELED: Did you update the key and location/region info?");
    }

    recognizer.stopContinuousRecognitionAsync();
};

recognizer.sessionStopped = (s, e) => {
    console.log("\n    Session stopped event.");
    recognizer.stopContinuousRecognitionAsync();
};

With everything set up, call startContinuousRecognitionAsync to start recognizing.

recognizer.startContinuousRecognitionAsync();

// make the following call at some point to stop recognition.
// recognizer.stopContinuousRecognitionAsync();

Dictation mode

speechConfig.enableDictation();

Change source language

speechConfig.speechRecognitionLanguage = "it-IT";

Improve recognition accuracy

const phraseList = sdk.PhraseListGrammar.fromRecognizer(recognizer);
phraseList.addPhrase("Supercalifragilisticexpialidocious");

If you need to clear your phrase list:

phraseList.clear();

For more details here...

Answer 3

To use Azure Voice Api, You need to get the authorize from the Azure Support team. If you didn't get it, you can't call it in website. Please check your debug console, you can get the Azure support link. And then fill in the require field and submit it to the support team.