How do I convert voice to text in iOS

Question

As far as I know , apple native framework doesn't have APIs for converting voice to text and we have to go for third party framework to do that and it has so many drawbacks like user has to microphone to convert from voice to text.

But I can find lots of information for converting text to voice but not the other way

Couldn't find any clear information about this and mostly it has so many uncertain things.

If someone could shed some light it'd be really great !

Answer 1

Here is the full code for the same:

import UIKit
import Speech

public class ViewController: UIViewController, SFSpeechRecognizerDelegate {
    // MARK: Properties

    private let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))!

    private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?

    private var recognitionTask: SFSpeechRecognitionTask?

    private let audioEngine = AVAudioEngine()

    @IBOutlet var textView : UITextView!

    @IBOutlet var recordButton : UIButton!

    // MARK: UIViewController

    public override func viewDidLoad() {
        super.viewDidLoad()

        // Disable the record buttons until authorization has been granted.
        recordButton.isEnabled = false
    }

    override public func viewDidAppear(_ animated: Bool) {
        speechRecognizer.delegate = self

        SFSpeechRecognizer.requestAuthorization { authStatus in
            /*
                The callback may not be called on the main thread. Add an
                operation to the main queue to update the record button's state.
            */
            OperationQueue.main.addOperation {
                switch authStatus {
                    case .authorized:
                        self.recordButton.isEnabled = true

                    case .denied:
                        self.recordButton.isEnabled = false
                        self.recordButton.setTitle("User denied access to speech recognition", for: .disabled)

                    case .restricted:
                        self.recordButton.isEnabled = false
                        self.recordButton.setTitle("Speech recognition restricted on this device", for: .disabled)

                    case .notDetermined:
                        self.recordButton.isEnabled = false
                        self.recordButton.setTitle("Speech recognition not yet authorized", for: .disabled)
                }
            }
        }
    }

    private func startRecording() throws {

        // Cancel the previous task if it's running.
        if let recognitionTask = recognitionTask {
            recognitionTask.cancel()
            self.recognitionTask = nil
        }

        let audioSession = AVAudioSession.sharedInstance()
        try audioSession.setCategory(AVAudioSessionCategoryRecord)
        try audioSession.setMode(AVAudioSessionModeMeasurement)
        try audioSession.setActive(true, with: .notifyOthersOnDeactivation)

        recognitionRequest = SFSpeechAudioBufferRecognitionRequest()

        guard let inputNode = audioEngine.inputNode else { fatalError("Audio engine has no input node") }
        guard let recognitionRequest = recognitionRequest else { fatalError("Unable to created a SFSpeechAudioBufferRecognitionRequest object") }

        // Configure request so that results are returned before audio recording is finished
        recognitionRequest.shouldReportPartialResults = true

        // A recognition task represents a speech recognition session.
        // We keep a reference to the task so that it can be cancelled.
        recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { result, error in
            var isFinal = false

            if let result = result {
                self.textView.text = result.bestTranscription.formattedString
                isFinal = result.isFinal
            }

            if error != nil || isFinal {
                self.audioEngine.stop()
                inputNode.removeTap(onBus: 0)

                self.recognitionRequest = nil
                self.recognitionTask = nil

                self.recordButton.isEnabled = true
                self.recordButton.setTitle("Start Recording", for: [])
            }
        }

        let recordingFormat = inputNode.outputFormat(forBus: 0)
        inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer: AVAudioPCMBuffer, when: AVAudioTime) in
            self.recognitionRequest?.append(buffer)
        }

        audioEngine.prepare()

        try audioEngine.start()

        textView.text = "(Go ahead, I'm listening)"
    }

    // MARK: SFSpeechRecognizerDelegate

    public func speechRecognizer(_ speechRecognizer: SFSpeechRecognizer, availabilityDidChange available: Bool) {
        if available {
            recordButton.isEnabled = true
            recordButton.setTitle("Start Recording", for: [])
        } else {
            recordButton.isEnabled = false
            recordButton.setTitle("Recognition not available", for: .disabled)
        }
    }

    // MARK: Interface Builder actions

    @IBAction func recordButtonTapped() {
        if audioEngine.isRunning {
            audioEngine.stop()
            recognitionRequest?.endAudio()
            recordButton.isEnabled = false
            recordButton.setTitle("Stopping", for: .disabled)
        } else {
            try! startRecording()
            recordButton.setTitle("Stop recording", for: [])
        }
    }
}