Leopard Speech-to-Text
iOS Quick Start

Platforms

• iOS (13.0+)

Requirements

• Xcode
• CocoaPods

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 Xcode.

2. Install CocoaPods

3. Import the Leopard Speech-to-Text iOS binding by adding the following line to Podfile:

pod 'Leopard-iOS'

4. Run the following from the project directory:

pod install

5. Add the following to the app's Info.plist file to enable recording with an iOS device's microphone

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

Model File

Add the Leopard Speech-to-Text model file in Xcode:

1. Create a model in Picovoice Console or use a default language model.
2. Add the model as a bundled resource by selecting Build Phases and adding it to Copy Bundle Resources step.

Usage

Create an instance of Leopard Speech-to-Text:

import Leopard

let accessKey = "${ACCESS_KEY}"
let modelPath = Bundle(for: type(of: self)).path(
        forResource: "${LEOPARD_MODEL_FILE}",
        ofType: "pv")!

do {
    let leopard = Leopard(accessKey: accessKey, modelPath: modelPath)
} catch { }

Alternatively, you can provide modelPath as an absolute path to the model file on device.

Transcribe an audio file either by passing the absolute path or an url to the file:

do {
    let audioPath = Bundle(for: type(of: self)).path(
      forResource: "${AUDIO_FILE_NAME}",
      ofType: "${AUDIO_FILE_EXTENSION}")
    let result = leopard.processFile(audioPath);
    print(result.transcript)
} catch let error as LeopardError {
    // handle error
} catch { }

Release resources explicitly when done with 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 iOS 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. Install dependencies:

cd leopard/demo/ios/LeopardDemo
pod install

2. Open the LeopardDemo.xcworkspace.

3. Replace "${YOUR_ACCESS_KEY_HERE}" in the file ViewController.swift with a valid AccessKey.

4. Go to Product > Scheme and select the scheme for the language you would like to demo (e.g. arDemo -> Arabic Demo, deDemo -> German Demo).

5. Run the demo with a simulator or connected iOS device.

Resources