feat: add TranscriptionManager orchestrating audio, WS, and output

MyVoxtral/MyVoxtral/Models/TranscriptionManager.swift

@@ -0,0 +1,99 @@
+import SwiftUI
+
+enum RecordingState: Equatable {
+    case idle
+    case recording
+    case error(String)
+}
+
+@MainActor
+final class TranscriptionManager: ObservableObject {
+    @Published var state: RecordingState = .idle
+    @Published var currentText: String = ""
+
+    private let audioCapture = AudioCapture()
+    private let wsClient = VoxtralWebSocketClient()
+    private let settings = AppSettings.shared
+    private var hasRetried = false
+
+    var isRecording: Bool { state == .recording }
+
+    func toggle() {
+        if isRecording {
+            stop()
+        } else {
+            start()
+        }
+    }
+
+    func start() {
+        guard settings.hasAPIKey else {
+            state = .error("No API key set. Open Settings.")
+            return
+        }
+
+        currentText = ""
+        hasRetried = false
+
+        wsClient.onEvent = { [weak self] event in
+            self?.handleEvent(event)
+        }
+
+        wsClient.connect(apiKey: settings.apiKey, delayMs: settings.streamingDelayMs)
+
+        audioCapture.onChunk = { [weak self] chunk in
+            Task { @MainActor in
+                self?.wsClient.sendAudio(chunk)
+            }
+        }
+
+        do {
+            try audioCapture.start()
+            state = .recording
+        } catch {
+            state = .error("Mic error: \(error.localizedDescription)")
+        }
+    }
+
+    func stop() {
+        audioCapture.stop()
+        wsClient.flush()
+        wsClient.disconnect()
+        state = .idle
+
+        if !currentText.isEmpty {
+            TranscriptionLogger.append(text: currentText)
+        }
+    }
+
+    private func handleEvent(_ event: VoxtralEvent) {
+        switch event {
+        case .sessionCreated:
+            break
+        case .textDelta(let text):
+            currentText += text
+            if settings.outputMode == .cursorInjection {
+                CursorInjector.typeText(text)
+            }
+        case .segment:
+            break
+        case .language:
+            break
+        case .done(let text):
+            if currentText.isEmpty {
+                currentText = text
+            }
+        case .error(let message):
+            if !hasRetried && state == .recording {
+                hasRetried = true
+                wsClient.disconnect()
+                wsClient.connect(apiKey: settings.apiKey, delayMs: settings.streamingDelayMs)
+            } else {
+                state = .error(message)
+                audioCapture.stop()
+            }
+        case .unknown:
+            break
+        }
+    }
+}