Picovoice Platform
Web Quick Start

Platforms

• Chrome & Chromium-based browsers
• Edge
• Firefox
• Safari

Requirements

• Picovoice Account and AccessKey
• Node.js 16+
• npm

Picovoice Account & AccessKey

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

Quick Start

Setup

1. Install Node.js.

2. Install the web-voice-processor and picovoice-web packages:

npm install @picovoice/picovoice-web @picovoice/web-voice-processor

Usage

To initialize Picovoice you'll need a Porcupine keyword file (.ppn) and model file (.pv), as well as a Rhino context file (.rhn) and model file (.pv). Place these files in the project's public directory or generate a base64 representation of the file using the built-in script:

npx pvbase64 -i ${PICOVOICE_INIT_FILE} -o ${BASE64_OUTPUT_FILE}

Create a PicovoiceWorker instance using public directory initialization files:

import {PicovoiceWorker} from "@picovoice/picovoice-web";

const porcupineKeyword = {publicPath: "${PPN_KEYWORD_PATH}"};
const wakeWordCallback = (detection) => {
    console.log(`Picovoice detected wake word: ${detection.label}`);
};
const porcupineModel = {publicPath: "${PPN_MODEL_PATH}"};
const rhinoContext = {publicPath: "${RHN_CONTEXT_PATH}"};
const inferenceCallback = (inference) => {
    if (inference.isUnderstood) {
        console.log(inference.intent)
        console.log(inference.slots)
    }
};
const rhinoModel = {publicPath: "${RHN_MODEL_PATH}"};

const picovoice = await PicovoiceWorker.create(
    ${ACCESS_KEY},
    porcupineKeyword,
    wakeWordCallback,
    porcupineModel,
    rhinoContext,
    inferenceCallback,
    rhinoModel
);

Subscribe the engine to the Web Voice Processor to start audio processing:

import {WebVoiceProcessor} from "@picovoice/web-voice-processor"

await WebVoiceProcessor.subscribe(picovoice);

Unsubscribe from Web Voice Processor to stop audio processing:

await WebVoiceProcessor.unsubscribe(picovoice);

Release resources explicitly when done with Picovoice:

picovoice.release();
picovoice.terminate();

Custom Wake Words & Contexts

Create custom keywords and contexts using the Picovoice Console. Train a Porcupine keyword to obtain a keyword file (.ppn) and a Rhino context to obtain a context file (.rhn). To use them with the Web SDK, train the keywords and contexts for the target platform Web (WASM). These model files can be used directly with publicPath, but, if base64 is preferable, convert to base64 JavaScript variable using the built-in pvbase64 script:

npx pvbase64 -i ${INPUT_BINARY_FILE}.{ppn/rhn} -o ${OUTPUT_BASE64_FILE}.js -n ${BASE64_VAR_NAME}

Similar to the model file (.pv), these files are saved in IndexedDB to be used by Web Assembly. Either base64 or publicPath must be set for each file to initialize Picovoice. If both are set, Picovoice will use the base64 model.

const picovoiceFile = {
  publicPath: "${FILE_RELATIVE_PATH}",
  // or
  base64: "${FILE_BASE64_STRING}",
}

Non-English Languages

In order to use Picovoice with different languages you need to use the corresponding model file (.pv) for the desired language. The model files for all supported languages are available in the Porcupine and Rhino GitHub repositories.

Demo

For the Picovoice Web SDK, there is a Web demo project available on the Picovoice GitHub repository.

Setup

Clone the Picovoice repository from GitHub:

git clone --recurse-submodules https://github.com/Picovoice/picovoice.git

Usage

1. Install the dependencies and use the start script with a language code to start the demo in the language of your choice (e.g. de -> German, ko -> Korean). To see a list of available languages, run start without a language code.

cd picovoice/demo/web
npm install
npm run start ${LANGUAGE}

2. Open http://localhost:5000 to view it in the browser.

Resources