Web Quick Start
- Chrome & Chromium-based browsers
- Picovoice Account and AccessKey
- Node.js 14+
Picovoice Account & AccessKey
Signup or Login to Picovoice Console to obtain your
Make sure to keep your
Install Node.js .
Install the web-voice-processor and picovoice-web packages:
Picovoice you'll need a
Porcupine keyword file (
and model file (
.pv), as well as a
Rhino context file (
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:
PicovoiceWorker instance using public directory initialization files:
Subscribe the engine to the Web Voice Processor to start audio processing:
Unsubscribe from Web Voice Processor to stop audio processing:
Release resources explicitly when done with Picovoice:
Custom Keywords & 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 (
To use them with the Web SDK, train the keywords and contexts for the target platform
These model files can be used directly with
publicPath, but, if
base64 is preferable, convert to base64
Similar to the model file (
.pv), these files are saved in IndexedDB to be used by Web Assembly.
publicPath must be set for each file to initialize Picovoice. If both are set, Picovoice will use
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.
For the Picovoice Web SDK, there is a Web demo project available on the Picovoice GitHub repository .
Clone the Picovoice repository from GitHub:
- Install dependencies and run:
- Open http://localhost:5000 to view it in the browser.