Rhino - 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 Rhino npm package:

npm install @picovoice/rhino-node

Usage

Create an instance of Rhino that infers intents from spoken commands within a given context:

const Rhino = require("@picovoice/rhino-node");

const contextPath = "${CONTEXT_FILE_PATH}";
const accessKey = "${ACCESS_KEY}"
const rhino = new Rhino(accessKey, contextPath);

Pass in frames of audio to the .process function:

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

let isFinalized = false;

while (!isFinalized) {
  const audioFrame = getNextAudioFrame();
  isFinalized = rhino.process(audioFrame);

  if (isFinalized) {
    const inference = rhino.getInference();
    if (inference.isUnderstood) {
        const intent = inference.intent;
        const slots = inference.slots;
        // take action based on inferred intent and slot values
    } else {
        // handle unsupported commands
    }
  }
}

Release resources explicitly when done with Rhino:

rhino.release()

Custom Contexts

Create custom contexts with the Picovoice Console using the Rhino Grammar. Download the custom context file (.rhn) and pass it into the Rhino constructor.

Non-English Languages

Use the corresponding model file (.pv) to infer non-English commands. The model files for all supported languages are available on the Rhino GitHub repository.

Pass in the model file to change the inference language:

const rhino = new Rhino(
    '${ACCESS_KEY}',
    '${CONTEXT_FILE_PATH}',
    0.5,
    true,
    '${MODEL_FILE_PATH}'
);

Demo

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

Setup

Install the Rhino demo package:

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

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

Usage

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

rhn-mic-demo --help

Ensure you have a working microphone connected to your system and run the following command to infer voice commands from the given context file:

rhn-mic-demo \
--access_key ${ACCESS_KEY} \
--context ${CONTEXT_FILE_PATH} \

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

Resources

Packages

• @picovoice/rhino-node
• @picovoice/rhino-node-demo

API

• rhino-node API Docs

GitHub

• Rhino Nodejs SDK on GitHub
• Rhino Nodejs Demos on GitHub

Benchmark

• Speech-to-Intent Benchmark

Further Reading

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