Cheetah Speech-to-Text
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 the Cheetah Streaming Speech-to-Text Web package:

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

Usage

Generate a custom Cheetah Streaming Speech-to-Text model from Picovoice Console or download the default model.

Put the model file in the project's public directory or generate a base64 model using the built-in script:

npx pvbase64 -i ${CHEETAH_PARAMS_PATH} -o ${OUTPUT_FILE_PATH}

Create a CheetahWorker instance using a base64 model or a model hosted in a public directory:

import { CheetahWorker } from "@picovoice/cheetah-web";
import cheetahParams from "${CHEETAH_PARAMS_BASE64_PATH}";

let transcript = "";
function transcriptCallback(cheetahTranscript: CheetahTranscript) {
  transcript += cheetahTranscript.transcript;
  if (cheetahTranscript.isEndpoint) {
    transcript += "\n";
  }
}

const cheetah = await CheetahWorker.create(
  "${ACCESS_KEY}",
  transcriptCallback,
  {
    base64: cheetahParams,
    // or
    publicPath: "${MODEL_RELATIVE_PATH}",
  }
);

Subscribe CheetahWorker to WebVoiceProcessor to start processing audio frames:

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

WebVoiceProcessor.subscribe(cheetah);

Once done, unsubscribe to stop processing audio frames:

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

WebVoiceProcessor.unsubscribe(cheetah);

Release resources explicitly when done with Cheetah:

await cheetah.release()

Non-English Languages

In order to use Cheetah with other languages, you need to use the corresponding model file (.pv) for the desired language. The model files for all supported languages are available on the Cheetah GitHub repository.

Demo

For the Cheetah Streaming Speech-to-Text Web SDK, there is a Web demo project available on the Cheetah Streaming Speech-to-Text GitHub repository.

Setup

Clone the Cheetah Streaming Speech-to-Text repository from GitHub:

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

Usage

1. Install dependencies:

cd cheetah/demo/react
npm install

2. Run the demo with the start script with a language code to start a local web server hosting the demo in the language of your choice (e.g. de -> German, es -> Spanish). To see a list of available languages, run start without a language code.

npm run start ${LANGUAGE}

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

Resources