Rhino Speech-to-Intent
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 get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Install Node.js.

2. Install the Web Voice Processor and Rhino Speech-to-Intent Web packages:

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

Usage

To initialize Rhino Speech-to-Intent you'll need a Rhino context file (.rhn) as well as a 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 ${RHINO_INIT_FILE} -o ${BASE64_OUTPUT_FILE}

Pass the path to the file (relative to the public directory) or use the base64 string:

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

Create a RhinoWorker that infers intent from spoken commands within a given context:

import { RhinoWorker } from "@picovoice/rhino-web";

const contextFileBase64 = // base64 of Rhino context file (.rhn)
const modelFilePublicPath = // base64 of Rhino model file (.pv)

function rhinoInferenceCallback(inference) {
   if (inference.isFinalized) {
      if (inference.isUnderstood) {
         const intent = inference.intent;
         const slots = inference.slots;
         // take action based on inferred intent and slot values
      } else {
         // handle unsupported commands
      }
   }
}

const rhino = await RhinoWorker.create(
   "${ACCESS_KEY}",
   { base64: contextFileBase64 },
   rhinoInferenceCallback,
   { base64: modelFileBase64 },
);

Subscribe RhinoWorker to WebVoiceProcessor to pass audio to the Rhino Speech-to-Intent engine:

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

WebVoiceProcessor.subscribe(rhino);

Once done, unsubscribe to stop processing audio frames:

WebVoiceProcessor.unsubscribe(rhino);

Release resources explicitly when done with Rhino Speech-to-Intent:

rhino.terminate();

Custom Contexts

Create custom contexts in the Picovoice Console using the Rhino Speech-to-Intent Grammar. Train and download a Rhino context file (.rhn) for the target platform Web (WASM). This model file can be used directly with publicPath, but, if base64 is preferable, convert the .rhn file to a base64 JavaScript variable using the built-in pvbase64 script:

npx pvbase64 -i ${CONTEXT_FILE}.rhn -o ${CONTEXT_BASE64}.js -n ${CONTEXT_BASE64_VAR_NAME}

Similar to the model file (.pv), context files (.rhn) are saved in IndexedDB to be used by Web Assembly. Either base64 or publicPath must be set for the context to instantiate Rhino. If both are set, Rhino Speech-to-Intent will use the base64 model.

const contextModel = {
  publicPath: "${CONTEXT_RELATIVE_PATH}",
  // or
  base64: "${CONTEXT_BASE64_STRING}",
}

Non-English Languages

In order to use Rhino Speech-to-Intent 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 Rhino GitHub repository.

Demo

For the Rhino Speech-to-Intent Web SDK, there is a Web demo project available on the Rhino GitHub repository.

Setup

Clone the Rhino Speech-to-Intent repository from GitHub:

git clone --recurse-submodules https://github.com/Picovoice/rhino.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 rhino/demo/web
npm install
npm run start ${LANGUAGE}

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

Resources