Cheetah Speech-to-Text
Node.js Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• NVIDIA Jetson Nano
• Raspberry Pi (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 cheetah-node npm package:

npm install @picovoice/cheetah-node

Usage

Create an instance of the engine:

const Cheetah = require("@picovoice/cheetah-node");

const accessKey = "${ACCESS_KEY}";
const cheetah = new Cheetah(accessKey);

Transcribe audio:

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

while (true) {
  const audioFrame = getNextAudioFrame();
  const [partialTranscript, isEndpoint] = cheetah.process(audioFrame);
  if (isEndpoint) {
    finalTranscript = cheetah.flush()
  }
}

Release resources explicitly when done with Cheetah:

cheetah.release()

Demo

For the Cheetah 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 Cheetah demo package:

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

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

Usage

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

cheetah_demo_mic --help

Ensure you have a working microphone connected to your system and run the following command to transcribe audio live:

cheetah_demo_mic --access_key ${ACCESS_KEY}

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

Resources