I want to include Speech Recognition in my app, for this I used the Speech Framework from Apple in combination with App Intents Framework. The app intent "Listen" starts the speech recognition. Now I have the problem that I keep getting the following error message:
*** Terminating app due to uncaught exception 'com.apple.coreaudio.avfaudio', reason: 'required condition is false: IsFormatSampleRateAndChannelCountValid(format)'
terminating with uncaught exception of type NSException
on the following line:
self.audioEngine.inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
This problem doesn't occur when I execute the same code with a simple button click, but ONYL with the App Intent "Listen". I am aware, that there is problem with the microphone that Siri uses while listening to the App intent. But how can I solve this issue? I did a lot of research and also tried it with async functions, but it didn't help
My Code:
import Speech
import UIKit
class TestVoice: UIControl, SFSpeechRecognizerDelegate {
let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))
var recognitionRequest : SFSpeechAudioBufferRecognitionRequest?
var recognitionTask : SFSpeechRecognitionTask?
let audioEngine = AVAudioEngine()
func stopRecording() {
self.audioEngine.stop()
self.recognitionRequest?.endAudio()
}
func setupSpeech() {
self.speechRecognizer?.delegate = self
SFSpeechRecognizer.requestAuthorization { (authStatus) in
switch authStatus {
case .authorized:
print("yes")
case .denied:
print("died")
case .restricted:
print("died")
case .notDetermined:
print("none")
}
OperationQueue.main.addOperation() {
}
}
}
func startRecording() -> Bool {
setupSpeech()
clearSessionData()
createAudioSession()
recognitionRequest = bufferRecRequest()
recognitionRequest?.shouldReportPartialResults = true
self.recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest!, resultHandler: { (result, error) in
var finished = false
if let result = result {
//do something
finished = result.isFinal
}
if error != nil || finished {
self.audioEngine.stop()
self.audioEngine.inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
}
})
let recordingFormat = self.audioEngine.inputNode.outputFormat(forBus: 0)
self.audioEngine.inputNode.installTap(onBus: 0, bufferSize: 2048, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
self.audioEngine.prepare()
do {
try self.audioEngine.start()
} catch {
print("audioEngine couldn't start because of an error.")
delegate?.showFeedbackError(title: "Sorry", message: "Your microphone is used somewhere else")
return false
}
return true
}
func clearSessionData(){
if recognitionTask != nil {
recognitionTask?.cancel()
recognitionTask = nil
}
}
func bufferRecRequest()->SFSpeechAudioBufferRecognitionRequest{
self.recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
}
return recognitionRequest
}
func createAudioSession()-> Bool{
do {
try AVAudioSession.sharedInstance().setCategory(AVAudioSession.Category.playAndRecord, options: .mixWithOthers)
} catch {
print("audioSession properties weren't set because of an error.")
delegate?.showFeedbackError(title: "Sorry", message: "Mic is busy")
return false
}
return true
}
}
The App Intent
import AppIntents
import UIKit
struct ListenIntent: AppIntent {
static var openAppWhenRun: Bool = true
@available(iOS 16, *)
static let title: LocalizedStringResource = "Listen"
static var description =
IntentDescription("Listens to the User")
let speechRecognizer = TestVoice()
func perform() throws -> some IntentResult & ProvidesDialog {
speechRecognizer.startRecording()
return .result(dialog: "Done")
}}
