dpearson2699/swift-ios-skills/skills-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
}

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"]

Mistake	Fix
Live audio requests only speech authorization	Require both speech and microphone permission.
Recognizer availability is checked once	Observe delegate availability changes and model loss of service.
Final/error/rollover paths perform different cleanup	Use one `stopTranscribing()` owner for engine stop, tap removal, `endAudio`, and task cancellation.
On-device mode is forced for every locale	Check `supportsOnDeviceRecognition` and provide a fallback.
One `SFSpeechRecognizer` task is used for long-form capture	Prefer SpeechAnalyzer on iOS 26+ or roll bounded segments while preserving committed transcript.
Finishing analyzer input is treated as session completion	Explicitly finalize through the last sample or cancel-and-finish.
Volatile SpeechAnalyzer results are appended	Replace the volatile range until a final result commits it.
A second recognition task starts before the first ends	Cancel/finish the active task and complete cleanup before replacement.

speech-recognition

Summary

SKILL.md

Speech Recognition

Contents

SpeechAnalyzer Strategy (iOS 26+)

SpeechAnalyzer setup checklist

SFSpeechRecognizer Setup

Creating a recognizer with locale

Monitoring availability changes

Authorization

Live Microphone Transcription

Pre-Recorded Audio File Recognition

On-Device vs Server Recognition

Handling Results

Partial vs final results

Accessing alternative transcriptions and confidence

Adding punctuation (iOS 16+)

Contextual strings

Common Mistakes

Review Checklist

References

Related skills