A SwiftUI text-to-speech app that parses SSML-like markup (e.g., <prosody>, etc.) to read text with dynamic pacing, pitch, and volume controls using AVSpeechSynthesizer. Features play/pause/stop controls and real-time adjustment sliders for speech rate, pitch, and volume.

ContentView.swift

//
//  ContentView.swift
//  DesiderataReader
//
//  Created by Xcode Developer on 10/11/25.
//

import SwiftUI
import AVFoundation
import Combine
import AVFAudio
import Observation

struct ContentView: View {
	@State private var speechManager = SpeechManager()
	@State private var isSpeaking: Bool = false

	var body: some View {
		NavigationView {
			VStack(spacing: 0) {
				Text(speechManager.displayText)
					.font(.system(.body, design: .serif).italic())
					.padding()
					.background(Color(.systemGray6))
					.cornerRadius(10)

				HStack(spacing: 40) {
					Button(action: {
						Task(priority: .high) {
							do {
								try await speechManager.togglePlay()
								isSpeaking.toggle()
								print("isSpeaking\t==\t\(speechManager.speaking)\t&&\t\(isSpeaking)")
							} catch {
								print("ERROR: isSpeaking\t==\t\(speechManager.speaking)\t&&\t\(isSpeaking)")
							}
						}
					}) {
						Image(systemName: isSpeaking ? "pause.circle.fill" : "play.circle.fill")
							.font(.system(size: 50))
							.foregroundColor(.blue)
					}
				}
				.padding()

				VStack {
					Text("Speech Settings")
						.font(.headline)

					//                    HStack {
					//                        Text("Rate:")
					//                        Slider(value: $speechManager.rate, in: 0...2, step: 1)
					//                            .onChange(of: <#T##Equatable#>, <#T##action: (Equatable, Equatable) -> Void##(Equatable, Equatable) -> Void##(_ oldValue: Equatable, _ newValue: Equatable) -> Void#>)
					//                        Text(String(format: "%.0f", speechManager.rate))
					//                            .frame(width: 50)
					//                    }

					HStack {
						Text("Rate:")
						Slider(value: $speechManager.rate, in: 0 ... 2, step: 1, onEditingChanged: { editing in
							if !editing {
								if isSpeaking {
									Task {
										speechManager.stop()
										speechManager.play()
									}
								}
							}
						})
						Text(String(format: "%.0f", speechManager.rate))
							.frame(width: 50)
					}

					HStack {
						Text("Pitch:")
						Slider(value: $speechManager.pitch, in: 0.8 ... 1.2)
						Text(String(format: "%.2f", speechManager.pitch))
							.frame(width: 50)
					}

					HStack {
						Text("Volume:")
						Slider(value: $speechManager.volume, in: 0.0 ... 1.0)
						Text(String(format: "%.2f", speechManager.volume))
							.frame(width: 50)
					}
				}
				.padding()
				.background(Color(.systemGray6))
				.cornerRadius(10)
				.padding(.horizontal)

				Spacer()
			}
			.navigationTitle("SSML + AVSpeechSynthesizer Sample")
			.navigationBarTitleDisplayMode(.inline)
			.navigationSubtitle("James Alan Bush (Build #fe96301")
		}
		.onReceive(NotificationCenter.default.publisher(for: .AVSpeechSynthesizerDidFinish)) { _ in
			print("AVSpeechSynthesizerDidFinish")
		}
	}
}

@Observable class SpeechManager: NSObject, AVSpeechSynthesizerDelegate {
	private let synthesizer: AVSpeechSynthesizer = AVSpeechSynthesizer() // private let synthesizer: AVSpeechSynthesizer = AVSpeechSynthesizer()
	private var currentUtterance: AVSpeechUtterance?

	private var _rate: Float = Float(1.0)
	var rate: Float {
		get { _rate }
		set {
			willChangeValue(forKey: "rate")
			_rate = newValue
			didChangeValue(forKey: "rate")
		}
	} // var rate: Float = 0.45
	var pitch: Float = 1.0
	var volume: Float = 0.8
	var speaking: Bool {
		synthesizer.isSpeaking ? true : false
	}

	// SSML-like markup for Desiderata
	// Note: AVSpeechSynthesizer doesn't support true SSML, so we'll simulate it with prosody controls
	// Replace this placeholder with the full text of Desiderata
	let ssmlText = """
	<speak>
	    <prosody rate="medium" pitch="high" volume="loud">
	        Go placidly amid the noise and the haste, and remember what peace there may be in silence. As far as possible, without surrender, be on good terms with all persons.

	        Speak your truth quietly and clearly; and listen to others, even to the dull and the ignorant; they too have their story.

	        Avoid loud and aggressive persons; they are vexatious to the spirit. If you compare yourself with others, you may become vain or bitter, for always there will be greater and lesser persons than yourself.

	        Enjoy your achievements as well as your plans. Keep interested in your own career, however humble; it is a real possession in the changing fortunes of time.

	        Exercise caution in your business affairs, for the world is full of trickery. But let this not blind you to what virtue there is; many persons strive for high ideals, and everywhere life is full of heroism.

	        Be yourself. Especially do not feign affection. Neither be cynical about love; for in the face of all aridity and disenchantment, it is as perennial as the grass.

	        Take kindly the counsel of the years, gracefully surrendering the things of youth.

	        Nurture strength of spirit to shield you in sudden misfortune. But do not distress yourself with dark imaginings. Many fears are born of fatigue and loneliness.

	        Beyond a wholesome discipline, be gentle with yourself. You are a child of the universe no less than the trees and the stars; you have a right to be here.

	        And whether or not it is clear to you, no doubt the universe is unfolding as it should. Therefore be at peace with God, whatever you conceive Him to be. And whatever your labors and aspirations, in the noisy confusion of life, keep peace in your soul. With all its sham, drudgery and broken dreams, it is still a beautiful world. Be cheerful. Strive to be happy.
	    </prosody>
	</speak>
	"""

	var displayText: String {
		// Strip SSML tags for display
		let pattern = "<[^>]+>"
		let regex = try! NSRegularExpression(pattern: pattern, options: [])
		let range = NSRange(location: 0, length: ssmlText.utf16.count)
		return regex.stringByReplacingMatches(in: ssmlText, options: [], range: range, withTemplate: "")
			.trimmingCharacters(in: .whitespacesAndNewlines)
	}

	override init() {
		super.init()
		synthesizer.delegate = self
	}

	func play() {
		let utterances = parseSSML(ssmlText)

		// Configure audio session for better quality
		do {
			try AVAudioSession.sharedInstance().setCategory(.playback, mode: .spokenAudio, options: .duckOthers)
			try AVAudioSession.sharedInstance().setActive(true)
		} catch {
			print("Failed to set up audio session: \(error)")
		}

		// Speak all utterances
		for utterance in utterances {
			utterance.rate = self.rate
			utterance.pitchMultiplier = self.pitch
			utterance.volume = self.volume
			//            currentUtterance = utterance
			synthesizer.speak(utterance)
		}
	}

	func pause() {
		synthesizer.pauseSpeaking(at: .word)
	}

	func stop() {
		synthesizer.stopSpeaking(at: .word)
	}

	func togglePlay() async throws -> Void {
		Task(priority: .high) {
			if (!synthesizer.isPaused && synthesizer.isSpeaking) {
				//                print("isSpeaking = \(self.speaking); pausing...")
				Task {
					synthesizer.pauseSpeaking(at: .word)
				}
			} else if (!synthesizer.isSpeaking && !synthesizer.isPaused) {
				//                print("Is not speaking, but is not paused; speaking...")
				self.play()
			} else if (!synthesizer.isSpeaking || synthesizer.isPaused) {
				//                print("Is not speaking, but is paused; continuing...")
				synthesizer.continueSpeaking()
			}
		}
	}

	private func parseSSML(_ ssml: String) -> [AVSpeechUtterance] {
		var utterances: [AVSpeechUtterance] = []

		// Split by prosody tags and breaks
		let lines = ssml.components(separatedBy: .newlines)
		var currentProsody: (rate: Float, pitch: Float, volume: Float) = (1.0, 1.0, 0.8)

		for line in lines {
			let trimmed = line.trimmingCharacters(in: .whitespacesAndNewlines)

			// Parse prosody tags
			if trimmed.contains("<prosody") {
				if trimmed.contains("rate=\"slow\"") {
					currentProsody.rate = 0.0
				} else if trimmed.contains("rate=\"medium\"") {
					currentProsody.rate = 1.0
				} else if trimmed.contains("rate=\"fast\"") {
					currentProsody.rate = 2.0
				}

				if trimmed.contains("pitch=\"low\"") {
					currentProsody.pitch = 0.9
				} else if trimmed.contains("pitch=\"medium\"") {
					currentProsody.pitch = 1.0
				} else if trimmed.contains("pitch=\"high\"") {
					currentProsody.pitch = 1.1
				}

				if trimmed.contains("volume=\"soft\"") {
					currentProsody.volume = 0.6
				} else if trimmed.contains("volume=\"loud\"") {
					currentProsody.volume = 1.0
				}
			}

			// Extract text content
			let textPattern = ">([^<]+)<"
			if let regex = try? NSRegularExpression(pattern: textPattern),
			   let match = regex.firstMatch(in: trimmed, range: NSRange(trimmed.startIndex..., in: trimmed)) {
				if let range = Range(match.range(at: 1), in: trimmed) {
					let text = String(trimmed[range]).trimmingCharacters(in: .whitespacesAndNewlines)

					if !text.isEmpty {
						let utterance = AVSpeechUtterance(string: text)
						utterance.rate = currentProsody.rate
						utterance.pitchMultiplier = currentProsody.pitch
						utterance.volume = currentProsody.volume
						utterance.voice = AVSpeechSynthesisVoice(language: "en-US")

						// Add pause after if there's a break tag
						if trimmed.contains("<break") {
							utterance.postUtteranceDelay = 0.5
						}

						utterances.append(utterance)
					}
				}
			}

			// Handle text without tags
			if !trimmed.contains("<") && !trimmed.contains(">") && !trimmed.isEmpty {
				let utterance = AVSpeechUtterance(string: trimmed)
				utterance.rate = currentProsody.rate
				utterance.pitchMultiplier = currentProsody.pitch
				utterance.volume = currentProsody.volume
				utterance.voice = AVSpeechSynthesisVoice(language: "en-US")
				utterances.append(utterance)
			}
		}

		return utterances
	}

	// AVSpeechSynthesizerDelegate methods
	func speechSynthesizer(_ synthesizer: AVSpeechSynthesizer, didFinish utterance: AVSpeechUtterance) {
		NotificationCenter.default.post(name: .AVSpeechSynthesizerDidFinish, object: nil)
	}
}

extension Notification.Name {
	static let AVSpeechSynthesizerDidFinish = Notification.Name("AVSpeechSynthesizerDidFinish")
}

#Preview {
	ContentView()
		.preferredColorScheme(.dark)
}

DesiderataReaderApp.swift

//
//  DesiderataReaderApp.swift
//  DesiderataReader
//
//  Created by Xcode Developer on 10/11/25.
//

import SwiftUI

@main
struct DesiderataReaderApp: App {
	var body: some Scene {
		WindowGroup {
			ContentView()
		}
	}
}