Voice-overlay in Swift

Hello, In this blog we are going to learn about the Voice-overlay in Swift

By using voice overlay you can easily search the data, place, etc from your ios application.

1. Create a view controller then you can proceed.

2. In your controller you need to add speech library.

this is the swift library Please follow the step below

import Speech

1	import Speech

3. Then you need to use this library from your controller please use below code

by using below code you can initialize the speech recognizer, then you need to use over the controller to search the data

private let speechRecognizer = SFSpeechRecognizer(locale: Locale.init(identifier: Defaults.language ?? "en"))
    private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
    private var recognitionTask: SFSpeechRecognitionTask?
    private let audioEngine = AVAudioEngine()

private let speechRecognizer = SFSpeechRecognizer(locale: Locale.init(identifier: Defaults.language ?? "en"))

private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?

private var recognitionTask: SFSpeechRecognitionTask?

private let audioEngine = AVAudioEngine()

4. Please ask the user for permission if the user not allow the permission then it will not accessable from the application then you have to allow from the device setting

SFSpeechRecognizer.requestAuthorization { (authStatus) in
            var isButtonEnabled = false
            switch authStatus {
            case .authorized:
                isButtonEnabled = true
            case .denied:
                isButtonEnabled = false
                print("User denied access to speech recognition")
                let alertController = UIAlertController (title: "", message: "Ask again to recognise audio".localized, preferredStyle: .alert)
                let settingsAction = UIAlertAction(title: "Settings".localized, style: .default) { (_) -> Void in
                    guard let settingsUrl = URL(string: UIApplication.openSettingsURLString) else {
                        return
                    }
                    if UIApplication.shared.canOpenURL(settingsUrl) {
                        UIApplication.shared.open(settingsUrl, completionHandler: { (success) in
                            print("Settings opened: \(success)") // Prints true
                        })
                    }
                }
                alertController.addAction(settingsAction)
                let cancelAction = UIAlertAction(title: "Cancel".localized, style: .default) { (_) -> Void in
                    self.dismiss(animated: true, completion: nil)
                }
                alertController.addAction(cancelAction)
                self.present(alertController, animated: true, completion: nil)
            case .restricted:
                isButtonEnabled = false
                print("Speech recognition restricted on this device")
            case .notDetermined:
                isButtonEnabled = false
                print("Speech recognition not yet authorized")
            }
            OperationQueue.main.addOperation() {
                    self.startRecording()
                } else {
                    self.navigationController?.popViewController(animated: true)
                }
            }
        }

SFSpeechRecognizer.requestAuthorization { (authStatus) in

var isButtonEnabled = false

switch authStatus {

case .authorized:

isButtonEnabled = true

case .denied:

isButtonEnabled = false

print("User denied access to speech recognition")

let alertController = UIAlertController (title: "", message: "Ask again to recognise audio".localized, preferredStyle: .alert)

let settingsAction = UIAlertAction(title: "Settings".localized, style: .default) { (_) -> Void in

guard let settingsUrl = URL(string: UIApplication.openSettingsURLString) else {

return

}

if UIApplication.shared.canOpenURL(settingsUrl) {

UIApplication.shared.open(settingsUrl, completionHandler: { (success) in

print("Settings opened: \(success)") // Prints true

})

}

alertController.addAction(settingsAction)

let cancelAction = UIAlertAction(title: "Cancel".localized, style: .default) { (_) -> Void in

self.dismiss(animated: true, completion: nil)

}

alertController.addAction(cancelAction)

self.present(alertController, animated: true, completion: nil)

case .restricted:

isButtonEnabled = false

print("Speech recognition restricted on this device")

case .notDetermined:

isButtonEnabled = false

print("Speech recognition not yet authorized")

}

OperationQueue.main.addOperation() {

self.startRecording()

} else {

self.navigationController?.popViewController(animated: true)

}

5. If the user provided the permission then it will start the recording

 let audioSession = AVAudioSession.sharedInstance()
        do {
            try audioSession.setCategory(AVAudioSession.Category.record, mode: AVAudioSession.Mode.default, options: [])
            try audioSession.setMode(AVAudioSession.Mode.measurement)
            try audioSession.setActive(true, options: .notifyOthersOnDeactivation)
        } catch {
            print("audioSession properties weren't set because of an error.")
        }
        recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
        let inputNode = audioEngine.inputNode
        guard let recognitionRequest = recognitionRequest else {
            fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
        }
        recognitionRequest.shouldReportPartialResults = true
        recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
            var isFinal = false
            if result != nil {
                print(result?.bestTranscription.formattedString as Any)
                self.detectedText.text = result?.bestTranscription.formattedString
                if self.detectedText.text != "" {
                    self.searchBtn.isHidden = false
                }
                isFinal = (result?.isFinal)!
            }
            if error != nil || isFinal {
                self.audioEngine.stop()
                inputNode.removeTap(onBus: 0)
                self.recognitionRequest = nil
                self.recognitionTask = nil
            }
        })
        let recordingFormat = inputNode.outputFormat(forBus: 0)
        inputNode.installTap(onBus: 0, bufferSize: 1, format: recordingFormat) { (buffer, when) in
            self.recognitionRequest?.append(buffer)
        }
        audioEngine.prepare()
        do {
            try audioEngine.start()
        } catch {
            print("audioEngine couldn't start because of an error.")
        }
        listeningLbl.text = "Listening".localized

let audioSession = AVAudioSession.sharedInstance()

do {

try audioSession.setCategory(AVAudioSession.Category.record, mode: AVAudioSession.Mode.default, options: [])

try audioSession.setMode(AVAudioSession.Mode.measurement)

try audioSession.setActive(true, options: .notifyOthersOnDeactivation)

} catch {

print("audioSession properties weren't set because of an error.")

}

recognitionRequest = SFSpeechAudioBufferRecognitionRequest()

let inputNode = audioEngine.inputNode

guard let recognitionRequest = recognitionRequest else {

fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")

}

recognitionRequest.shouldReportPartialResults = true

recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in

var isFinal = false

if result != nil {

print(result?.bestTranscription.formattedString as Any)

self.detectedText.text = result?.bestTranscription.formattedString

if self.detectedText.text != "" {

self.searchBtn.isHidden = false

}

isFinal = (result?.isFinal)!

}

if error != nil || isFinal {

self.audioEngine.stop()

inputNode.removeTap(onBus: 0)

self.recognitionRequest = nil

self.recognitionTask = nil

}

})

let recordingFormat = inputNode.outputFormat(forBus: 0)

inputNode.installTap(onBus: 0, bufferSize: 1, format: recordingFormat) { (buffer, when) in

self.recognitionRequest?.append(buffer)

}

audioEngine.prepare()

do {

try audioEngine.start()

} catch {

print("audioEngine couldn't start because of an error.")

}

listeningLbl.text = "Listening".localized

Please manage the text as per you

Thank you for reading this article. I hope this article helped you to implement Advanced usage of Voice-overlay in Swift,

After that, if you want to read more articles regarding iOS Development click here or if you want to read more about Voice-overlay click here.

For other technical blogs, please click here.

Ranjit kumar 27 May 2022

. . .

Leave a Comment Cancel Reply

Message Sent!