Porcupine - Node.js Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• BeagleBone
• NVIDIA Jetson Nano
• Raspberry Pi (2, 3, 4)

Requirements

• Picovoice Account & AccessKey
• Node.js 10+
• npm

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Install Node.js.

2. Install the porcupine-node npm package:

npm install @picovoice/porcupine-node

Usage

Create an instance of Porcupine that detects the included built-in wake words porcupine and bumblebee with sensitivities of 0.5 and 0.65, respectively.

const {
  Porcupine,
  BuiltinKeyword,
}= require("@picovoice/porcupine-node");

const accessKey = "${ACCESS_KEY}"
let porcupine = new Porcupine(
    accessKey,
    [BuiltinKeyword.GRASSHOPPER, BuiltinKeyword.BUMBLEBEE],
    [0.5, 0.65]
);

Pass in frames of audio to the .process function:

function getNextAudioFrame() {
  // ...
  return audioFrame;
}

while (true) {
  const audioFrame = getNextAudioFrame();
  const keywordIndex = porcupine.process(audioFrame);
  if (keywordIndex === 0) {
    // detected `porcupine
  } else if (keywordIndex === 1) {
    // detected `bumblebee`
  }
}

Release resources explicitly when done with Porcupine:

porcupine.release()

Custom Keywords

Create custom keywords using the Picovoice Console. Download the custom wake word file (.ppn) and create an instance of Porcupine by passing in the path to the keyword file.

const porcupine = new Porcupine(
  '${ACCESS_KEY}',
  ['${KEYWORD_FILE_PATH}'],
  [0.5]
);

Non-English Languages

Use the corresponding model file (.pv) to detect non-English wake words. The model files for all supported languages are available on the Porcupine GitHub repository.

Pass in the model file to change the detection language:

const porcupine = new Porcupine(
  '${ACCESS_KEY}',
  ['${KEYWORD_FILE_PATH}'],
  [0.5],
  '${MODEL_FILE_PATH}'
);

Demo

For the Porcupine Node.js SDK, we offer demo applications that demonstrate how to use the Wake Word engine on real-time audio streams (i.e. microphone input) and audio files.

Setup

Install the Porcupine demo package:

npm install -g @picovoice/porcupine-node-demo

This package installs command-line utilities for the Porcupine Nodejs demos.

Usage

Use the --help flag to see the usage options for the demo:

ppn-mic-demo --help

Ensure you have a working microphone connected to your system and run the following command to detect the built-in keyword porcupine:

ppn-mic-demo \
--access_key ${ACCESS_KEY} \
--keywords porcupine \

For more information on our Porcupine demos for Nodejs, head over to our GitHub repository.

Resources

Packages

• @picovoice/porcupine-node
• @picovoice/porcupine-node-demo

API

• porcupine-node API Docs

GitHub

• Porcupine Nodejs SDK on GitHub
• Porcupine Nodejs Demos on GitHub

Benchmark

• Wake Word Benchmark

Further Reading

• Computer! Tea, Earl Grey, Hot: Offline Voice on NodeJS
• Computer! Tea, Earl Grey, Hot: Offline Voice on NodeJS, Part II