You are 100% correct.
The utterance aloud completed but nothing else worked.
I mistakenly thought the process would remain in memory until the completion of speech and the associated delegates fired.
For those who may need a working solution, here it is.
class SpeakerTest: NSObject, AVSpeechSynthesizerDelegate {
let synth = AVSpeechSynthesizer()
override init() {
super.init()
synth.delegate = self
}
func isSandboxEnvironment() -> Bool
{
let environ = ProcessInfo.processInfo.environment
return ( environ["APP_SANDBOX_CONTAINER_ID"] != nil )
}
func speechSynthesizer(_ synthesizer: AVSpeechSynthesizer, didFinish utterance: AVSpeechUtterance) {
print("Utterance didFinish")
}
func speechSynthesizer(_ synthesizer: AVSpeechSynthesizer,
willSpeakRangeOfSpeechString characterRange: NSRange,
utterance: AVSpeechUtterance)
{
print("speaking range: \(characterRange)")
}
func selectVoice(targetSpeaker: String, defLangCode: String) -> AVSpeechSynthesisVoice
{
var usedVoice = AVSpeechSynthesisVoice(language: defLangCode) // should be the default voice
let userCode = AVSpeechSynthesisVoice.currentLanguageCode()
let voices = AVSpeechSynthesisVoice.speechVoices()
for voice in voices {
// print("\(voice.identifier) \(voice.name) \(voice.quality) \(voice.language)")
if (voice.name.lowercased() == targetSpeaker.lowercased())
{
usedVoice = AVSpeechSynthesisVoice(identifier: voice.identifier)
break
}
}
// ensure we return a valid voice
if (usedVoice == nil) {usedVoice = AVSpeechSynthesisVoice(language: userCode) }
return usedVoice!
}
func speak(_ string: String, speaker: String) {
let utterance = AVSpeechUtterance(string: string)
utterance.voice = selectVoice(targetSpeaker: speaker, defLangCode: "en-US")
synth.speak(utterance)
}
func writeToBuffer(_ stringToSpeak: String, speaker: String)
{
print("entering writeToBuffer")
let utterance = AVSpeechUtterance(string: stringToSpeak)
utterance.voice = selectVoice(targetSpeaker: speaker, defLangCode: "en-US")
synth.write(utterance) { (buffer: AVAudioBuffer) in
print("executing synth.write")
guard let pcmBuffer = buffer as? AVAudioPCMBuffer else {
fatalError("unknown buffer type: \(buffer)")
}
if ( pcmBuffer.frameLength == 0 ) {
print("buffer is empty")
} else {
print("buffer has content \(buffer)")
}
}
}
func writeToFile(_ stringToSpeak: String, speaker: String)
{
let utterance = AVSpeechUtterance(string: stringToSpeak)
var output : AVAudioFile?
let desktop = "~/Desktop"
let fileName = "Utterance_Test.caf" // not in sandbox
var tempPath = desktop + "/" + fileName
tempPath = (tempPath as NSString).expandingTildeInPath
// if sandboxed, it goes in the container
if ( isSandboxEnvironment() ) { tempPath = "Utterance_Test.caf" }
utterance.voice = selectVoice(targetSpeaker: speaker, defLangCode: "en-US")
synth.write(utterance) { (buffer: AVAudioBuffer) in
guard let pcmBuffer = buffer as? AVAudioPCMBuffer else {
fatalError("unknown buffer type: \(buffer)")
}
if ( pcmBuffer.frameLength == 0 ) {
// done
} else {
// append buffer to file
if ( output == nil ) {
let bufferSettings = utterance.voice?.audioFileSettings
output = try! AVAudioFile( forWriting: URL(fileURLWithPath: tempPath),settings: bufferSettings!)
}
try! output?.write(from: pcmBuffer)
}
}
}
}
class ViewController: NSViewController {
let speechDelivery = SpeakerTest()
override func viewDidLoad() {
super.viewDidLoad()
let targetSpeaker = "Allison"
var sentenceToSpeak = "This writes to buffer and disk."
sentenceToSpeak += "Also, 'didFinish' and 'willSpeakRangeOfSpeechString' delegates fire."
speechDelivery.writeToBuffer(sentenceToSpeak, speaker: targetSpeaker)
speechDelivery.speak(sentenceToSpeak, speaker: targetSpeaker)
speechDelivery.writeToFile(sentenceToSpeak, speaker: targetSpeaker)
}
override var representedObject: Any? {
didSet {
// Update the view, if already loaded.
}
}
}
