transcribe()

// Simple transcription
let text = try await RunAnywhere.transcribe(audioData)
print("You said: \(text)")

import RunAnywhere
import ONNXRuntime

// Register ONNX module (at app launch)
@MainActor
func setup() {
    ONNX.register()
}

// Load STT model
try await RunAnywhere.loadSTTModel("whisper-base-onnx")

public static func transcribe(_ audioData: Data) async throws -> String

public static func transcribeWithOptions(
    _ audioData: Data,
    options: STTOptions
) async throws -> STTOutput

public static func transcribeBuffer(
    _ buffer: AVAudioPCMBuffer,
    language: String? = nil
) async throws -> STTOutput

public struct STTOutput: Sendable {
    public let text: String                       // Transcribed text
    public let confidence: Float?                 // Confidence score (0-1)
    public let wordTimestamps: [WordTimestamp]?   // Per-word timing
    public let detectedLanguage: String?          // Detected language code
    public let alternatives: [STTAlternative]?    // Alternative transcriptions
    public let metadata: TranscriptionMetadata?   // Processing info
}

import AVFoundation

class AudioRecorder: ObservableObject {
    private var audioRecorder: AVAudioRecorder?
    private let audioSession = AVAudioSession.sharedInstance()

    func startRecording() async throws {
        try audioSession.setCategory(.playAndRecord, mode: .default)
        try audioSession.setActive(true)

        let url = FileManager.default.temporaryDirectory
            .appendingPathComponent("recording.wav")

        let settings: [String: Any] = [
            AVFormatIDKey: Int(kAudioFormatLinearPCM),
            AVSampleRateKey: 16000,
            AVNumberOfChannelsKey: 1,
            AVLinearPCMBitDepthKey: 16,
            AVLinearPCMIsFloatKey: false
        ]

        audioRecorder = try AVAudioRecorder(url: url, settings: settings)
        audioRecorder?.record()
    }

    func stopAndTranscribe() async throws -> String {
        guard let recorder = audioRecorder else { return "" }

        recorder.stop()
        let audioData = try Data(contentsOf: recorder.url)

        return try await RunAnywhere.transcribe(audioData)
    }
}

let output = try await RunAnywhere.transcribeWithOptions(
    audioData,
    options: STTOptions(
        language: "en",
        enableWordTimestamps: true
    )
)

print("Full text: \(output.text)")

if let timestamps = output.wordTimestamps {
    for word in timestamps {
        print("\(word.word): \(word.startTime)s - \(word.endTime)s")
    }
}

// Auto-detect language
let output = try await RunAnywhere.transcribeWithOptions(
    audioData,
    options: STTOptions()
)
print("Detected language: \(output.detectedLanguage ?? "unknown")")

// Force specific language
let spanishOutput = try await RunAnywhere.transcribeWithOptions(
    audioData,
    options: STTOptions(language: "es")
)

struct VoiceInputView: View {
    @StateObject private var recorder = AudioRecorder()
    @State private var transcription = ""
    @State private var isRecording = false
    @State private var isProcessing = false

    var body: some View {
        VStack(spacing: 20) {
            // Transcription display
            Text(transcription)
                .frame(maxWidth: .infinity, minHeight: 100, alignment: .topLeading)
                .padding()
                .background(Color.gray.opacity(0.1))
                .cornerRadius(12)

            // Record button
            Button(action: toggleRecording) {
                ZStack {
                    Circle()
                        .fill(isRecording ? Color.red : Color.blue)
                        .frame(width: 80, height: 80)

                    if isProcessing {
                        ProgressView()
                            .tint(.white)
                    } else {
                        Image(systemName: isRecording ? "stop.fill" : "mic.fill")
                            .font(.title)
                            .foregroundColor(.white)
                    }
                }
            }
            .disabled(isProcessing)

            Text(isRecording ? "Tap to stop" : "Tap to record")
                .font(.caption)
                .foregroundColor(.secondary)
        }
        .padding()
    }

    func toggleRecording() {
        if isRecording {
            stopRecording()
        } else {
            startRecording()
        }
    }

    func startRecording() {
        Task {
            do {
                try await recorder.startRecording()
                isRecording = true
            } catch {
                transcription = "Failed to start recording: \(error)"
            }
        }
    }

    func stopRecording() {
        isRecording = false
        isProcessing = true

        Task {
            do {
                let text = try await recorder.stopAndTranscribe()
                await MainActor.run {
                    transcription = text
                    isProcessing = false
                }
            } catch {
                await MainActor.run {
                    transcription = "Transcription failed: \(error)"
                    isProcessing = false
                }
            }
        }
    }
}

// Load a model
try await RunAnywhere.loadSTTModel("whisper-base-onnx")

// Check if loaded
let isLoaded = await RunAnywhere.isSTTModelLoaded

// Get current model
let model = await RunAnywhere.currentSTTModel

// Unload when done
try await RunAnywhere.unloadSTTModel()

do {
    let text = try await RunAnywhere.transcribe(audioData)
    print(text)
} catch let error as SDKError {
    switch error.code {
    case .modelNotFound:
        print("Load an STT model first")
    case .emptyAudioBuffer:
        print("Audio data is empty")
    case .processingFailed:
        print("Transcription failed: \(error.message)")
    default:
        print("Error: \(error.localizedDescription)")
    }
}