Offline Voice AI in a browser may seem contradictory. Doesn't using a web browser mean you’re online? But even if connected to the Internet, offline voice recognition in-browser means eliminating variable latency and intrinsic privacy. Local voice recognition also unlocks always-listening behaviour that is impractical to perform continuously with cloud-based services.

Try It

Here is a demonstration application that uses the Porcupine wake word engine and the Rhino Speech-to-Intent engines to control lights in a home. All speech recognition is private, offline, and in-browser.

LIVING ROOMBEDROOMCLOSETBATHROOMPANTRYHALLWAYKITCHEN

The speech-to-intent engine didn't understand the command.

Loading ...

What's under the Hood?

Offline web voice AI is challenging. We had to extend our in-house deep learning framework to run on WebAssembly with SIMD support. These models run in the background using Web Workers . Together with the Web Audio API , these provided the foundation for accessing microphone data in the browser and processing it. We have abstracted these cutting-edge web technologies in Picovoice SDKs for the Web.

Start Building

Start building with Leopard speech-to-text for free.

Open-Source Demos

Below are demos (Vanilla) JavaScript, React, Vue, and Angular. These are minimal applications that show how to integrate the Picovoice SDKs into web applications.

How do I create custom wake words or speech-to-intent contexts for the web?

You can use the Picovoice Console to create wake words and design and train speech to intent contexts.