How to Convert Text to Speech Using Google Text-to-Speech API in JavaScript

Install Google Cloud Client Library

• Make sure you've installed the Node.js environment in your project since we will be using JavaScript along with Node.js modules.

 

• Install the essential Node.js client library for accessing Google Cloud Text-to-Speech API. Execute the following command to install the necessary Google Cloud library:

npm install @google-cloud/text-to-speech

Import and Authenticate the Client Library

• Import the `@google-cloud/text-to-speech` library in your JavaScript file to access the Text-to-Speech functionalities.

 

• Authenticate the library using service account credentials. These credentials are usually stored in a JSON file.

const textToSpeech = require('@google-cloud/text-to-speech');
const fs = require('fs');
const util = require('util');

// Creates a client
const client = new textToSpeech.TextToSpeechClient();

Create Synthesis Request

• Prepare a request object that specifies the text you want to convert to speech as well as the voice and audio format configurations.

 

• Set up the input text and the associated voice parameters like the language code and gender of the voice.

const request = {
  input: { text: 'Hello, world!' },
  // Select the language and SSML Voice Gender (optional)
  voice: { languageCode: 'en-US', ssmlGender: 'NEUTRAL' },
  // Select the type of audio encoding
  audioConfig: { audioEncoding: 'MP3' },
};

Synthesize Speech

• Invoke the synthesize speech method on the Text-to-Speech client, providing the request object. This method converts the provided text into synthesized audio content.

 

• Handle the promise returned by the synthesis function, which contains the audio data.

async function synthesizeText() {
  // Performs the Text-to-Speech request
  const [response] = await client.synthesizeSpeech(request);
  
  // Write the binary audio content to a local file
  const writeFile = util.promisify(fs.writeFile);
  await writeFile('output.mp3', response.audioContent, 'binary');
  console.log('Audio content written to file: output.mp3');
}

synthesizeText();

Run Your Script and Handle Errors

• Execute your Node.js script to convert the specified text to speech and save the resulting audio to a file.

 

• Implement error handling mechanisms to capture and report any issues encountered during the synthesis process.

node your_script.js

• Check the console for messages indicating the progress and outcome of the request, and verify the generated audio file for correctness.