Syntax Speech to Text

node-google-speech-to-text.js

import speech from '@google-cloud/speech';
import fs from 'fs';
import dotenv from 'dotenv';

dotenv.config();

async function main() {
  const client = new speech.SpeechClient();

  const config = {
    encoding: 'MP3',
    sampleRateHertz: 44100,
    languageCode: 'en-US',
    diarizationConfig: {
      enableSpeakerDiarization: true,
      minSpeakerCount: 2,
      maxSpeakerCount: 3,
    },
    metadata: {
      interactionType: 'PROFESSIONALLY_PRODUCED',
      // 541511 Custom Computer Programming Services 	Web (i.e., Internet) page design services, custom
      industryNaicsCodeOfAudio: 541511,
      microphoneDistance: 'NEARFIELD',
      originalMediaType: 'AUDIO',
      recordingDeviceType: 'OTHER_INDOOR_DEVICE',
      recordingDeviceName: 'Cardioid Microphone',
      originalMimeType: 'audio/mp3',
      audioTopic: 'Syntax Podcast',
    },
    speechContexts: [
      {
        phrases: [
          'syntax',
          'Hasty Treat',
          'Wes Bos',
          'Scott Tolinski',
          'tuples',
          'Log Rocket',
          'logrocket.com',
        ],
      },
    ],
  };

  const audio = {
    // uri: 'gs://syntax/Syntax287.mp3',
    uri: 'gs://syntax/clip.mp3',
  };

  const request = {
    config,
    audio,
  };

  // Detects speech in the audio file. This creates a recognition job that you
  // can wait for now, or get its result later.
  const [operation] = await client.longRunningRecognize(request);
  // Get a Promise representation of the final result of the job
  const [response] = await operation.promise();
  const transcription = response.results
    .map(result => result.alternatives[0].transcript)
    .join('\n');
  console.log(`Transcription: ${transcription}`);

  fs.writeFileSync('syntax3.txt', transcription);
}

main().catch(console.error);