Leopard Speech-to-Text
Flutter Quick Start

Platforms

• Flutter (2.8.1+)
• Android (5.0+, API 21+)
• iOS (13.0+)

Requirements

• Flutter SDK
• Android SDK (21+)
• JDK (8+)
• Xcode (13+)

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 Flutter SDK.

2. Run flutter doctor to determine any missing requirements.

3. Add the Leopard Speech-to-Text plugin to your app project by referencing it in pubspec.yaml:

dependencies:
  leopard_flutter: ^<version>

4. 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

Add the Leopard Speech-to-Text model file to your Flutter application:

1. Create a model in Picovoice Console or use a default language model.
2. Add the model file to an assets folder in your project directory.
3. Add the asset to your pubspec.yaml:

flutter:
  assets:
    - assets/leopard_model.pv

4. In this example, the path to the model file in code would then be as follows:

String modelPath = "assets/leopard_model.pv";

Usage

An instance of Leopard Speech-to-Text is created by passing a model file path into its static constructor create:

import 'package:leopard_flutter/leopard.dart';

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

void createLeopard() async {
    try {
        _leopard = await Leopard.create(accessKey, modelPath);
    } on LeopardException catch (err) {
        // handle Leopard init error
    }
}

Transcribe an audio file by passing in the path:

try {
    LeopardTranscript result = await _leopard.processFile("${AUDIO_FILE_PATH}");
    print(result.transcript);
} on LeopardException catch (err) { }

When done, resources have to be released explicitly:

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 Flutter SDK, we offer demo applications that demonstrate how to use the Speech-to-Text engine on audio recordings.

Setup

Clone the Leopard Speech-to-Text repository from GitHub using HTTPS:

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

Usage

1. Run the prepare_demo script with a language code to set up the demo in the language of your choice (e.g. de -> German, ko -> Korean). To see a list of available languages, run prepare_demo without a language code.

cd leopard/demo/flutter
dart scripts/prepare_demo.dart ${LANGUAGE}

2. Replace {YOUR_ACCESS_KEY_HERE} with a valid AccessKey in the demo/flutter/lib/main.dart file:

3. Build and deploy the demo to your device:

flutter run

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

Resources