node package manager
Stop wasting time. Easily manage code sharing in your team. Create a free org »

@google-cloud/speech

Google Cloud Platform logo

Google Cloud Speech API: Node.js Client

release level CircleCI AppVeyor codecov

Node.js idiomatic client for Speech API.

The Cloud Speech API enables easy integration of Google speech recognition technologies into developer applications. Send audio and receive a text transcription from the Cloud Speech API service.

Read more about the client libraries for Cloud APIs, including the older Google APIs Client Libraries, in Client Libraries Explained.

Table of contents:

Quickstart

Before you begin

  1. Select or create a Cloud Platform project.

    Go to the projects page

  2. Enable billing for your project.

    Enable billing

  3. Enable the Google Cloud Speech API API.

    Enable the API

  4. Set up authentication with a service account so you can access the API from your local workstation.

Installing the client library

npm install --save @google-cloud/speech

Using the client library

// Imports the Google Cloud client library
const speech = require('@google-cloud/speech');
const fs = require('fs');
 
// Your Google Cloud Platform project ID
const projectId = 'your-project-id';
 
// Creates a client
const client = new speech.SpeechClient({
  projectId: projectId,
});
 
// The name of the audio file to transcribe
const fileName = './resources/audio.raw';
 
// 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: 'LINEAR16',
  sampleRateHertz: 16000,
  languageCode: 'en-US',
};
const request = {
  audio: audio,
  config: config,
};
 
// Detects speech in the audio file
client
  .recognize(request)
  .then(data => {
    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);
  });

Samples

Samples are in the samples/ directory. The samples' README.md has instructions for running the samples.

Sample Source Code Try it
Speech Recognition source code Open in Cloud Shell

The Speech API Node.js Client API Reference documentation also contains samples.

Versioning

This library follows Semantic Versioning.

This library is considered to be in beta. This means it is expected to be mostly stable while we work toward a general availability release; however, complete stability is not guaranteed. We will address issues and requests against beta libraries with a high priority.

More Information: Google Cloud Platform Launch Stages

Contributing

Contributions welcome! See the Contributing Guide.

License

Apache Version 2.0

See LICENSE