Leopard Speech-to-Text
React Native Quick Start

Platforms

• Android (5.0+, API 21+)
• iOS (13.0+)

Requirements

• Picovoice Account and AccessKey
• React Native 0.62.2+

Picovoice Account & AccessKey

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

Quick Start

Setup

1. Set up the React Native environment.

2. Install the npm packages:

   • @picovoice/leopard-react-native

npm install @picovoice/leopard-react-native

3. Enable the proper permissions for recording with the hardware's microphone on both iOS and Android:

<key>NSMicrophoneUsageDescription</key>
<string>[Permission explanation]</string>

<uses-permission android:name="android.permission.RECORD_AUDIO" />
<uses-permission android:name="android.permission.INTERNET" />

Model File

Create a custom model using the Picovoice Console or use a default language model.

Android

To add a Leopard Speech-to-Text model file to your Android application, add the file as a bundled resource by placing it under the assets directory of your Android application.

iOS

To add a Leopard Speech-to-Text model file to your iOS application, add the file as a bundled resource by selecting Build Phases in Xcode and adding it to the Copy Bundle Resources step.

Usage

Create an instance of Leopard Speech-to-Text using a custom model from Picovoice console or using a default model.

import {Leopard, LeopardErrors} from '@picovoice/leopard-react-native';

const accessKey = "{ACCESS_KEY}"  // AccessKey obtained from Picovoice Console (https://console.picovoice.ai/)
const modelPath = "{CHEETAH_MODEL_PATH}" // path relative to the assets folder or absolute path to file on device

try {
    const leopard = await Leopard.create(accessKey, modelPath)
} catch (err: any) {
  if (err instanceof LeopardErrors) {
    // handle error
  }
}

Transcribe an audio file by providing an absolute path to the file:

const { transcript, words } = await leopard.processFile("${AUDIO_FILE_PATH}")
console.log(transcript)

Transcribe raw audio data (sample rate of 16 kHz, 16-bit linearly encoded and 1 channel):

const getAudioData = () => {
  // ...
}

const { transcript, words } = await leopard.process(getAudioData())
console.log(transcript)

Free resources used by Leopard Speech-to-Text:

leopard.delete()

Word Metadata

Along with the transcript, Leopard Speech-to-Text returns metadata for each transcribed word. Available metadata items are:

• Start Time: Indicates when the word started in the transcribed audio. Value is in seconds.
• End Time: Indicates when the word ended in the transcribed audio. Value is in seconds.
• Confidence: Leopard Speech-to-Text's confidence that the transcribed word is accurate. It is a number within [0, 1].
• Speaker Tag: If speaker diarization is enabled on initialization, the speaker tag is a non-negative integer identifying unique speakers, with 0 reserved for unknown speakers. If speaker diarization is not enabled, the value will always be -1.

Demo

For the Leopard Speech-to-Text React Native SDK, there is a React Native demo project available on the Picovoice GitHub repository.

Setup

Clone the Picovoice repository from GitHub:

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

Usage

1. Install dependencies and setup environment:

cd leopard/demo/react-native

npm run android-install
# or
npm run ios-install

2. Connect a mobile device or launch a simulator. Then run the android-run or ios-run and replace ${LANGUAGE} with the language code of your choice (e.g. de -> German, ko -> Korean). To see a list of available languages, command without a language code.

npm run android-run ${LANGUAGE}
# or
npm run ios-run ${LANGUAGE}

For more information on our Leopard Speech-to-Text demos for React Native, head over to our GitHub repository.

Resources