AVSpeechSynthesizer does not speak after using SFSpeechRecognizer

Question

So I built a simple app that does speech recognition using SFSpeechRecognizer and displays the converted speech to text in a UITextView on the screen. Now I'm trying to make the phone speak that displayed text. It doesn't work for some reason. AVSpeechSynthesizer speak function works only before SFSpeechRecognizer was used. For instance, when the app launches, it has some welcome text displayed in the UITextView, if I tap the speak button, the phone will speak out the welcome text. Then if I do record (for speech recognition), the recognized speech will be displayed in the UITextView. Now I want the phone to speak that text, but unfortunately it doesn't.

here is the code

import UIKit
import Speech
import AVFoundation


class ViewController: UIViewController, SFSpeechRecognizerDelegate, AVSpeechSynthesizerDelegate {

    @IBOutlet weak var textView: UITextView!
    @IBOutlet weak var microphoneButton: UIButton!

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

    private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
    private var recognitionTask: SFSpeechRecognitionTask?
    private let audioEngine = AVAudioEngine()

    override func viewDidLoad() {
        super.viewDidLoad()

        microphoneButton.isEnabled = false

        speechRecognizer.delegate = self

        SFSpeechRecognizer.requestAuthorization { (authStatus) in

            var isButtonEnabled = false

            switch authStatus {
            case .authorized:
                isButtonEnabled = true

            case .denied:
                isButtonEnabled = false
                print("User denied access to speech recognition")

            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.microphoneButton.isEnabled = isButtonEnabled
            }
        }
    }

    @IBAction func speakTapped(_ sender: UIButton) {
        let string = self.textView.text
        let utterance = AVSpeechUtterance(string: string!)
        let synthesizer = AVSpeechSynthesizer()
        synthesizer.delegate = self
        synthesizer.speak(utterance)
    }
    @IBAction func microphoneTapped(_ sender: AnyObject) {
        if audioEngine.isRunning {
            audioEngine.stop()
            recognitionRequest?.endAudio()
            microphoneButton.isEnabled = false
            microphoneButton.setTitle("Start Recording", for: .normal)
        } else {
            startRecording()
            microphoneButton.setTitle("Stop Recording", for: .normal)
        }
    }

    func startRecording() {

        if recognitionTask != nil {  //1
            recognitionTask?.cancel()
            recognitionTask = nil
        }

        let audioSession = AVAudioSession.sharedInstance()  //2
        do {
            try audioSession.setCategory(AVAudioSessionCategoryRecord)
            try audioSession.setMode(AVAudioSessionModeMeasurement)
            try audioSession.setActive(true, with: .notifyOthersOnDeactivation)
        } catch {
            print("audioSession properties weren't set because of an error.")
        }

        recognitionRequest = SFSpeechAudioBufferRecognitionRequest()  //3

        guard let inputNode = audioEngine.inputNode else {
            fatalError("Audio engine has no input node")
        }  //4

        guard let recognitionRequest = recognitionRequest else {
            fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
        } //5

        recognitionRequest.shouldReportPartialResults = true  //6

        recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in  //7

            var isFinal = false  //8

            if result != nil {

                self.textView.text = result?.bestTranscription.formattedString  //9
                isFinal = (result?.isFinal)!
            }

            if error != nil || isFinal {  //10
                self.audioEngine.stop()
                inputNode.removeTap(onBus: 0)

                self.recognitionRequest = nil
                self.recognitionTask = nil

                self.microphoneButton.isEnabled = true
            }
        })

        let recordingFormat = inputNode.outputFormat(forBus: 0)  //11
        inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
            self.recognitionRequest?.append(buffer)
        }

        audioEngine.prepare()  //12

        do {
            try audioEngine.start()
        } catch {
            print("audioEngine couldn't start because of an error.")
        }

        textView.text = "Say something, I'm listening!"

    }

    func speechRecognizer(_ speechRecognizer: SFSpeechRecognizer, availabilityDidChange available: Bool) {
        if available {
            microphoneButton.isEnabled = true
        } else {
            microphoneButton.isEnabled = false
        }
    }
}

Answer 1

You should change this line of the startRecording method from:

try audioSession.setCategory(AVAudioSessionCategoryRecord)            

to:

try audioSession.setCategory(AVAudioSessionCategoryPlayAndRecord)