[WIP] Improvements: improve Audio Input Activation / Deactivation process so it is faster

internal/audio/audio_mute.go

@@ -9,6 +9,11 @@ var audioMuteState struct {
 	mu    sync.RWMutex
 }
 
+var microphoneMuteState struct {
+	muted bool
+	mu    sync.RWMutex
+}
+
 func SetAudioMuted(muted bool) {
 	audioMuteState.mu.Lock()
 	audioMuteState.muted = muted
@@ -20,3 +25,15 @@ func IsAudioMuted() bool {
 	defer audioMuteState.mu.RUnlock()
 	return audioMuteState.muted
 }
+
+func SetMicrophoneMuted(muted bool) {
+	microphoneMuteState.mu.Lock()
+	microphoneMuteState.muted = muted
+	microphoneMuteState.mu.Unlock()
+}
+
+func IsMicrophoneMuted() bool {
+	microphoneMuteState.mu.RLock()
+	defer microphoneMuteState.mu.RUnlock()
+	return microphoneMuteState.muted
+}

internal/audio/core_handlers.go

@@ -119,29 +119,42 @@ func (s *AudioControlService) StopMicrophone() error {
 	return nil
 }
 
-// MuteMicrophone sets the microphone mute state by controlling the microphone process
+// MuteMicrophone sets the microphone mute state by controlling data flow (like audio output)
 func (s *AudioControlService) MuteMicrophone(muted bool) error {
 	if muted {
-		// Mute: Stop microphone process
+		// Mute: Control data flow, don't stop subprocess (like audio output)
-		err := s.StopMicrophone()
+		SetMicrophoneMuted(true)
-		if err != nil {
+		s.logger.Info().Msg("microphone muted (data flow disabled)")
-			s.logger.Error().Err(err).Msg("failed to stop microphone during mute")
-			return err
-		}
-		s.logger.Info().Msg("microphone muted (process stopped)")
 	} else {
-		// Unmute: Start microphone process
+		// Unmute: Ensure subprocess is running, then enable data flow
-		err := s.StartMicrophone()
+		if !s.sessionProvider.IsSessionActive() {
-		if err != nil {
+			return errors.New("no active session for microphone unmute")
-			s.logger.Error().Err(err).Msg("failed to start microphone during unmute")
-			return err
 		}
-		s.logger.Info().Msg("microphone unmuted (process started)")
+
+		audioInputManager := s.sessionProvider.GetAudioInputManager()
+		if audioInputManager == nil {
+			return errors.New("audio input manager not available")
+		}
+
+		// Start subprocess if not already running (async, non-blocking)
+		if !audioInputManager.IsRunning() {
+			go func() {
+				if err := audioInputManager.Start(); err != nil {
+					s.logger.Error().Err(err).Msg("failed to start microphone during unmute")
+				}
+			}()
+		}
+
+		// Enable data flow immediately
+		SetMicrophoneMuted(false)
+		s.logger.Info().Msg("microphone unmuted (data flow enabled)")
 	}
 
-	// Broadcast microphone mute state change via WebSocket
+	// Broadcast microphone state change via WebSocket
 	broadcaster := GetAudioEventBroadcaster()
-	broadcaster.BroadcastAudioDeviceChanged(!muted, "microphone_mute_changed")
+	sessionActive := s.sessionProvider.IsSessionActive()
+	// With the new approach, "running" means "not muted"
+	broadcaster.BroadcastMicrophoneStateChanged(!muted, sessionActive)
 
 	return nil
 }
@@ -254,16 +267,13 @@ func (s *AudioControlService) IsAudioOutputActive() bool {
 	return !IsAudioMuted() && IsAudioRelayRunning()
 }
 
-// IsMicrophoneActive returns whether the microphone subprocess is running
+// IsMicrophoneActive returns whether the microphone is active (not muted)
 func (s *AudioControlService) IsMicrophoneActive() bool {
 	if !s.sessionProvider.IsSessionActive() {
 		return false
 	}
 
-	audioInputManager := s.sessionProvider.GetAudioInputManager()
+	// With the new unified approach, microphone "active" means "not muted"
-	if audioInputManager == nil {
+	// This matches how audio output works - active means not muted
-		return false
+	return !IsMicrophoneMuted()
-	}
-
-	return audioInputManager.IsRunning()
 }

internal/audio/input_microphone_manager.go

@@ -91,6 +91,11 @@ func (aim *AudioInputManager) WriteOpusFrame(frame []byte) error {
 		return nil // Not running, silently drop
 	}
 
+	// Check mute state - drop frames if microphone is muted (like audio output)
+	if IsMicrophoneMuted() {
+		return nil // Muted, silently drop
+	}
+
 	// Use ultra-fast validation for critical audio path
 	if err := ValidateAudioFrame(frame); err != nil {
 		aim.logComponentError(AudioInputManagerComponent, err, "Frame validation failed")
@@ -128,6 +133,11 @@ func (aim *AudioInputManager) WriteOpusFrameZeroCopy(frame *ZeroCopyAudioFrame)
 		return nil // Not running, silently drop
 	}
 
+	// Check mute state - drop frames if microphone is muted (like audio output)
+	if IsMicrophoneMuted() {
+		return nil // Muted, silently drop
+	}
+
 	if frame == nil {
 		atomic.AddInt64(&aim.metrics.FramesDropped, 1)
 		return nil

ui/src/components/popovers/AudioControlPopover.tsx

@@ -61,14 +61,14 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
   // Use WebSocket-based audio events for real-time updates
   const { 
     audioMuted, 
+    microphoneState,
     isConnected: wsConnected 
   } = useAudioEvents();
   
   // WebSocket-only implementation - no fallback polling
   
-  // Microphone state from props
+  // Microphone state from props (keeping hook for legacy device operations)
   const {
-    isMicrophoneActive,
     startMicrophone,
     stopMicrophone,
     syncMicrophoneState,
@@ -82,6 +82,9 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
   const isMuted = audioMuted ?? false;
   const isConnected = wsConnected;
   
+  // Use WebSocket microphone state instead of hook state for real-time updates
+  const isMicrophoneActiveFromWS = microphoneState?.running ?? false;
+  
 
   
   // Audio devices
@@ -206,24 +209,29 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
     }
     
     setLastClickTime(now);
+    setIsLoading(true);
     
     try {
-      if (isMicrophoneActive) {
+      if (isMicrophoneActiveFromWS) {
-        // Microphone is active: stop the microphone process and WebRTC tracks
+        // Mute: Use unified microphone mute API (like audio output)
-        const result = await stopMicrophone();
+        const resp = await api.POST("/microphone/mute", { muted: true });
-        if (!result.success && result.error) {
+        if (!resp.ok) {
-          notifications.error(result.error.message);
+          throw new Error(`Failed to mute microphone: ${resp.status}`);
         }
+        // WebSocket will handle the state update automatically
       } else {
-        // Microphone is inactive: start the microphone process and WebRTC tracks
+        // Unmute: Use unified microphone mute API (like audio output)
-        const result = await startMicrophone(selectedInputDevice);
+        const resp = await api.POST("/microphone/mute", { muted: false });
-        if (!result.success && result.error) {
+        if (!resp.ok) {
-          notifications.error(result.error.message);
+          throw new Error(`Failed to unmute microphone: ${resp.status}`);
         }
+        // WebSocket will handle the state update automatically
       }
     } catch (error) {
       const errorMessage = error instanceof Error ? error.message : "Failed to toggle microphone";
       notifications.error(errorMessage);
+    } finally {
+      setIsLoading(false);
     }
   };
 
@@ -232,7 +240,7 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
     setSelectedInputDevice(deviceId);
     
     // If microphone is currently active (unmuted), restart it with the new device
-    if (isMicrophoneActive) {
+    if (isMicrophoneActiveFromWS) {
       try {
         // Stop current microphone
         await stopMicrophone();
@@ -317,26 +325,21 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
           
           <div className="flex items-center justify-between rounded-lg bg-slate-50 p-3 dark:bg-slate-700">
             <div className="flex items-center gap-3">
-              {isMicrophoneActive ? (
+              {isMicrophoneActiveFromWS ? (
                 <MdMic className="h-5 w-5 text-green-500" />
               ) : (
                 <MdMicOff className="h-5 w-5 text-red-500" />
               )}
               <span className="font-medium text-slate-900 dark:text-slate-100">
-                {isMicrophoneActive ? "Unmuted" : "Muted"}
+                {isMicrophoneActiveFromWS ? "Unmuted" : "Muted"}
               </span>
             </div>
             <Button
               size="SM"
-              theme={isMicrophoneActive ? "danger" : "primary"}
+              theme={isMicrophoneActiveFromWS ? "danger" : "primary"}
-              text={
+              text={isMicrophoneActiveFromWS ? "Disable" : "Enable"}
-                isStarting ? "Enabling..." : 
-                isStopping ? "Disabling..." : 
-                isMicrophoneActive ? "Disable" : "Enable"
-              }
               onClick={handleToggleMicrophoneMute}
-              disabled={isStarting || isStopping || isToggling}
+              disabled={isLoading}
-              loading={isStarting || isStopping}
             />
           </div>
           
@@ -378,7 +381,7 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
                 </option>
               ))}
             </select>
-            {isMicrophoneActive && (
+            {isMicrophoneActiveFromWS && (
                <p className="text-xs text-slate-500 dark:text-slate-400">
                  Changing device will restart the microphone
                </p>
@@ -415,7 +418,7 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
         </div>
 
         {/* Microphone Quality Settings */}
-        {isMicrophoneActive && (
+        {isMicrophoneActiveFromWS && (
           <div className="space-y-3">
             <div className="flex items-center gap-2">
               <MdMic className="h-4 w-4 text-slate-600 dark:text-slate-400" />
@@ -429,13 +432,13 @@ export default function AudioControlPopover({ microphone }: AudioControlPopoverP
                 <button
                   key={`mic-${quality}`}
                   onClick={() => handleMicrophoneQualityChange(parseInt(quality))}
-                  disabled={isStarting || isStopping || isToggling}
+                  disabled={isLoading}
                   className={cx(
                     "rounded-md border px-3 py-2 text-sm font-medium transition-colors",
                     currentMicrophoneConfig?.Quality === parseInt(quality)
                       ? "border-green-500 bg-green-50 text-green-700 dark:bg-green-900/20 dark:text-green-300"
                       : "border-slate-200 bg-white text-slate-700 hover:bg-slate-50 dark:border-slate-600 dark:bg-slate-700 dark:text-slate-300 dark:hover:bg-slate-600",
-                    (isStarting || isStopping || isToggling) && "opacity-50 cursor-not-allowed"
+                    isLoading && "opacity-50 cursor-not-allowed"
                   )}
                 >
                   {label}