TypeScript icon, indicating that this package has built-in type declarations

2.0.1 • Public • Published

Leopard Binding for Web

Leopard Speech-to-Text Engine

Made in Vancouver, Canada by Picovoice

Leopard is an on-device speech-to-text engine. Leopard is:

  • Private; All voice processing runs locally.
  • Accurate
  • Compact and Computationally-Efficient
  • Cross-Platform:
    • Linux (x86_64), macOS (x86_64, arm64), Windows (x86_64)
    • Android and iOS
    • Chrome, Safari, Firefox, and Edge
    • Raspberry Pi (4, 3) and NVIDIA Jetson Nano


  • Chrome / Edge
  • Firefox
  • Safari


IndexedDB is required to use Leopard in a worker thread. Browsers without IndexedDB support (i.e. Firefox Incognito Mode) should use Leopard in the main thread.


Using yarn:

yarn add @picovoice/leopard-web

or using npm:

npm install --save @picovoice/leopard-web


Leopard requires a valid Picovoice AccessKey at initialization. AccessKey acts as your credentials when using Leopard SDKs. You can get your AccessKey for free. Make sure to keep your AccessKey secret. Signup or Login to Picovoice Console to get your AccessKey.


Create a model in Picovoice Console or use one of the default language models found in lib/common.

For the web packages, there are two methods to initialize Leopard.

Public Directory

NOTE: Due to modern browser limitations of using a file URL, this method does not work if used without hosting a server.

This method fetches the model file from the public directory and feeds it to Leopard. Copy the model file into the public directory:



NOTE: This method works without hosting a server, but increases the size of the model file roughly by 33%.

This method uses a base64 string of the model file and feeds it to Leopard. Use the built-in script pvbase64 to base64 your model file:


The output will be a js file which you can import into any file of your project. For detailed information about pvbase64, run:

npx pvbase64 -h

Leopard Model

Leopard saves and caches your model file in IndexedDB to be used by WebAssembly. Use a different customWritePath variable to hold multiple models and set the forceWrite value to true to force re-save a model file.

Either base64 or publicPath must be set to instantiate Leopard. If both are set, Leopard will use the base64 model.

const leopardModel = {
  publicPath: ${MODEL_RELATIVE_PATH},
  // or
  base64: ${MODEL_BASE64_STRING},

  // Optionals
  customWritePath: "leopard_model",
  forceWrite: false,
  version: 1,

Init options

Set enableAutomaticPunctuation to true, if you wish to enable punctuation in transcript.

// Optional
const options = {
  enableAutomaticPunctuation: true

Initialize Leopard

Create an instance of Leopard in the main thread:

const handle = await Leopard.create(
  options // optional options

Or create an instance of Leopard in a worker thread:

const handle = await LeopardWorker.create(
  options // optional options

Process Audio Frames

The process result is an object with:

  • transcript: A string containing the transcribed data.
  • words: A list of objects containing a word, startSec, endSec, and confidence. Each object indicates the start, end time and confidence (between 0 and 1) of the word.
function getAudioData(): Int16Array {
  ... // function to get audio data
  return new Int16Array();

const result = await handle.process(getAudioData());

For processing using worker, you may consider transferring the buffer instead for performance:

let pcm = new Int16Array();
const result = await handle.process(pcm, {
  transfer: true,
  transferCallback: (data) => { pcm = data }

Clean Up

Clean up used resources by Leopard or LeopardWorker:

await handle.release();


Terminate LeopardWorker instance:

await handle.terminate();


For example usage refer to our Web demo application.

Package Sidebar


npm i @picovoice/leopard-web

Weekly Downloads






Unpacked Size

3.3 MB

Total Files


Last publish


  • albho
  • dynamix70
  • erismikpico
  • ilavery
  • kenarsa
  • kyeo