Speech Recognition

import Speech

// Default locale (user's current language)
let recognizer = SFSpeechRecognizer()

// Specific locale
let recognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))

// Check if recognition is available for this locale
guard let recognizer, recognizer.isAvailable else {
    print("Speech recognition not available")
    return
}

final class SpeechManager: NSObject, SFSpeechRecognizerDelegate {
    private let recognizer = SFSpeechRecognizer()!

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

    func speechRecognizer(
        _ speechRecognizer: SFSpeechRecognizer,
        availabilityDidChange available: Bool
    ) {
        // Update UI — disable record button when unavailable
    }
}

import Speech
import AVFoundation

func requestPermissions() async -> Bool {
    let speechStatus = await withCheckedContinuation { continuation in
        SFSpeechRecognizer.requestAuthorization { status in
            continuation.resume(returning: status)
        }
    }
    guard speechStatus == .authorized else { return false }

    let micStatus: Bool
    if #available(iOS 17, *) {
        micStatus = await AVAudioApplication.requestRecordPermission()
    } else {
        micStatus = await withCheckedContinuation { continuation in
            AVAudioSession.sharedInstance().requestRecordPermission { granted in
                continuation.resume(returning: granted)
            }
        }
    }
    return micStatus
}

import Speech
import AVFoundation

final class LiveTranscriber {
    private let recognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))!
    private let audioEngine = AVAudioEngine()
    private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
    private var recognitionTask: SFSpeechRecognitionTask?

    func startTranscribing() throws {
        // Cancel any in-progress task
        recognitionTask?.cancel()
        recognitionTask = nil

        // Configure audio session
        let audioSession = AVAudioSession.sharedInstance()
        try audioSession.setCategory(.record, mode: .measurement, options: .duckOthers)
        try audioSession.setActive(true, options: .notifyOthersOnDeactivation)

        // Create request
        let request = SFSpeechAudioBufferRecognitionRequest()
        request.shouldReportPartialResults = true
        self.recognitionRequest = request

        // Start recognition task
        recognitionTask = recognizer.recognitionTask(with: request) { result, error in
            if let result {
                let text = result.bestTranscription.formattedString
                print("Transcription: \(text)")

                if result.isFinal {
                    self.stopTranscribing()
                }
            }
            if let error {
                print("Recognition error: \(error)")
                self.stopTranscribing()
            }
        }

        // Install audio tap
        let inputNode = audioEngine.inputNode
        let recordingFormat = inputNode.outputFormat(forBus: 0)
        inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) {
            buffer, _ in
            request.append(buffer)
        }

        audioEngine.prepare()
        try audioEngine.start()
    }

    func stopTranscribing() {
        audioEngine.stop()
        audioEngine.inputNode.removeTap(onBus: 0)
        recognitionRequest?.endAudio()
        recognitionRequest = nil
        recognitionTask?.cancel()
        recognitionTask = nil
    }
}

func transcribeFile(at url: URL) async throws -> String {
    guard let recognizer = SFSpeechRecognizer(), recognizer.isAvailable else {
        throw SpeechError.unavailable
    }
    let request = SFSpeechURLRecognitionRequest(url: url)
    request.shouldReportPartialResults = false

    return try await withCheckedThrowingContinuation { continuation in
        var didResume = false
        recognizer.recognitionTask(with: request) { result, error in
            guard !didResume else { return }
            if let error {
                didResume = true
                continuation.resume(throwing: error)
            } else if let result, result.isFinal {
                didResume = true
                continuation.resume(
                    returning: result.bestTranscription.formattedString
                )
            }
        }
    }
}

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

// Check if on-device is supported for this locale
if recognizer.supportsOnDeviceRecognition {
    let request = SFSpeechAudioBufferRecognitionRequest()
    request.requiresOnDeviceRecognition = true  // Force on-device
}

let request = SFSpeechAudioBufferRecognitionRequest()
request.shouldReportPartialResults = true  // default is true

recognizer.recognitionTask(with: request) { result, error in
    guard let result else { return }

    if result.isFinal {
        // Final transcription — recognition is complete
        let final = result.bestTranscription.formattedString
    } else {
        // Partial result — may change as more audio is processed
        let partial = result.bestTranscription.formattedString
    }
}

recognizer.recognitionTask(with: request) { result, error in
    guard let result else { return }

    // Best transcription
    let best = result.bestTranscription

    // All alternatives (sorted by confidence, descending)
    for transcription in result.transcriptions {
        for segment in transcription.segments {
            print("\(segment.substring): \(segment.confidence)")
        }
    }
}

let request = SFSpeechAudioBufferRecognitionRequest()
request.addsPunctuation = true

let request = SFSpeechAudioBufferRecognitionRequest()
request.contextualStrings = ["SwiftUI", "Xcode", "CloudKit"]

// ❌ DON'T: Only request speech authorization for live audio
SFSpeechRecognizer.requestAuthorization { status in
    // Missing microphone permission — audio engine will fail
    self.startRecording()
}

// ✅ DO: Request both permissions before recording
SFSpeechRecognizer.requestAuthorization { status in
    guard status == .authorized else { return }
    AVAudioSession.sharedInstance().requestRecordPermission { granted in
        guard granted else { return }
        self.startRecording()
    }
}

// ❌ DON'T: Assume recognizer stays available after initial check
let recognizer = SFSpeechRecognizer()!
// Recognition may fail if network drops or locale changes

// ✅ DO: Monitor availability via delegate
recognizer.delegate = self
func speechRecognizer(
    _ speechRecognizer: SFSpeechRecognizer,
    availabilityDidChange available: Bool
) {
    recordButton.isEnabled = available
}

// ❌ DON'T: Leave audio engine running after recognition finishes
recognizer.recognitionTask(with: request) { result, error in
    if result?.isFinal == true {
        // Audio engine still running, wasting resources and battery
    }
}

// ✅ DO: Clean up all audio resources
recognizer.recognitionTask(with: request) { result, error in
    if result?.isFinal == true || error != nil {
        self.audioEngine.stop()
        self.audioEngine.inputNode.removeTap(onBus: 0)
        self.recognitionRequest?.endAudio()
        self.recognitionRequest = nil
    }
}

// ❌ DON'T: Force on-device without checking support
let request = SFSpeechAudioBufferRecognitionRequest()
request.requiresOnDeviceRecognition = true // Ignored unless the recognizer supports it

// ✅ DO: Check support before requiring on-device
if recognizer.supportsOnDeviceRecognition {
    request.requiresOnDeviceRecognition = true
} else {
    // Fall back to server-based or inform user
}

// ❌ DON'T: Start one long continuous recognition session
func startRecording() {
    // SFSpeechRecognizer tasks can be cut off after about 60 seconds
}

// ✅ DO: roll the segment before the limit and let cleanup end audio once
func scheduleRecognitionRollover() {
    recognitionTimer = Timer.scheduledTimer(withTimeInterval: 55, repeats: false) { [weak self] _ in
        self?.commitLatestPartialText()
        self?.stopTranscribing()     // owns endAudio(), tap removal, and task cancellation
        try? self?.startTranscribing()
    }
}

// ❌ DON'T: Only finish the AsyncStream and expect result streams to close
inputBuilder.finish()

// ✅ DO: explicitly finish or cancel the analyzer session
let lastSampleTime = try await analyzer.analyzeSequence(inputSequence)
if let lastSampleTime {
    try await analyzer.finalizeAndFinish(through: lastSampleTime)
} else {
    try analyzer.cancelAndFinishNow()
}

// ✅ Replace volatile text with the finalized result for the same audio range
for try await result in transcriber.results {
    if result.isFinal {
        volatileTranscript = AttributedString()
        finalizedTranscript.append(result.text)
    } else {
        volatileTranscript = result.text
    }
}

// ❌ DON'T: Start a new task without canceling the previous one
func startRecording() {
    recognitionTask = recognizer.recognitionTask(with: request) { ... }
    // Previous task is still running — undefined behavior
}

// ✅ DO: Cancel existing task before creating a new one
func startRecording() {
    recognitionTask?.cancel()
    recognitionTask = nil
    recognitionTask = recognizer.recognitionTask(with: request) { ... }
}