Google Voice Recognition API example

voice-recog.js

// We've followed documentation links and played with the example code a bit:
// Start here: https://cloud.google.com/speech
// If you need an audio editor, try Audacity:
// https://www.audacityteam.org
//
// usage: node voice-recog.js soundfile.flac en-US
//
// The second argument is the language code (e.g. en-US, pt-BR, fr-CA...)


// Imports the Google Cloud client library
const speech = require('@google-cloud/speech');
const fs = require('fs');

// Your Google Cloud Platform project ID
// You'll get this information and more once you register an application
// and install the Google Cloud Platform command line tools. 
const projectId = 'your-project-id-here';

// Creates a client
const client = new speech.SpeechClient({
  projectId: projectId,
});

// The name of the audio file to transcribe
const fileName = process.argv[2];
const lang = process.argv[3] || 'en-US';

// Reads a local audio file and converts it to base64
const file = fs.readFileSync(fileName);
const audioBytes = file.toString('base64');

// The audio file's encoding, sample rate in hertz, and BCP-47 language code
const audio = {
  content: audioBytes,
};
const config = {
  encoding: 'FLAC',
  sampleRateHertz: 44100,
  languageCode: lang,
};
const request = {
  audio: audio,
  config: config,
};

// Detects speech in the audio file
client
  .recognize(request)
  .then((data) => { // Looking at the response object
    console.log('Full response:', data[0].results[0].alternatives)
    return data
  })
  .then(data => { // Actual response processing
    const response = data[0];
    const transcription = response.results
      .map(result => result.alternatives[0].transcript)
      .join('\n');
    console.log(`Transcription: ${transcription}`);
  })
  .catch(err => {
    console.error('ERROR:', err);
  });