Merge 432303e228 into 83caa8f82d

Makefile

@@ -1,5 +1,3 @@
-.PHONY: setup_toolchain build_audio_deps dev_env lint lint-go lint-ui lint-fix lint-go-fix lint-ui-fix ui-lint
-
 # Clone the rv1106-system toolchain to $HOME/.jetkvm/rv1106-system
 setup_toolchain:
 	bash tools/setup_rv1106_toolchain.sh

README.md

@@ -13,7 +13,7 @@
 
 
 
-JetKVM is a high-performance, open-source KVM over IP (Keyboard, Video, Mouse, **Audio**) solution designed for efficient remote management of computers, servers, and workstations. Whether you're dealing with boot failures, installing a new operating system, adjusting BIOS settings, or simply taking control of a machine from afar, JetKVM provides the tools to get it done effectively.
+JetKVM is a high-performance, open-source KVM over IP (Keyboard, Video, Mouse, Audio) solution designed for efficient remote management of computers, servers, and workstations. Whether you're dealing with boot failures, installing a new operating system, adjusting BIOS settings, or simply taking control of a machine from afar, JetKVM provides the tools to get it done effectively.
 
 
 
@@ -22,7 +22,7 @@ JetKVM is a high-performance, open-source KVM over IP (Keyboard, Video, Mouse, *
 ## Features
 
 - **Ultra-low Latency** - 1080p@60FPS video with 30-60ms latency using H.264 encoding. Smooth mouse, keyboard, and audio for responsive remote control.
-- **First-Class Audio Support** - JetKVM now supports bidirectional, low-latency audio streaming using a dual-subprocess architecture with ALSA and Opus integration via CGO. Features both audio output (PC→Browser) and audio input (Browser→PC) with dedicated subprocesses for optimal performance and isolation.
+- **First-Class Audio Support** - JetKVM supports bidirectional, low-latency audio streaming using a dual-subprocess architecture with ALSA and Opus integration via CGO. Features both audio output (PC→Browser) and audio input (Browser→PC) with dedicated subprocesses for optimal performance and isolation.
 - **Free & Optional Remote Access** - Remote management via JetKVM Cloud using WebRTC.
 - **Open-source software** - Written in Golang (with CGO for audio) on Linux. Easily customizable through SSH access to the JetKVM device.
 
@@ -38,11 +38,9 @@ The best place to search for answers is our [Documentation](https://jetkvm.com/d
 
 If you've found an issue and want to report it, please check our [Issues](https://github.com/jetkvm/kvm/issues) page. Make sure the description contains information about the firmware version you're using, your platform, and a clear explanation of the steps to reproduce the issue.
 
-
-
 # Development
 
-JetKVM is written in Go & TypeScript, with some C for low-level integration. **Audio support uses a sophisticated dual-subprocess architecture with CGO, ALSA, and Opus integration for bidirectional streaming with complete process isolation.**
+JetKVM is written in Go & TypeScript, with some C for low-level integration
 
 The project contains two main parts: the backend software (Go, CGO) that runs on the KVM device, and the frontend software (React/TypeScript) that is served by the KVM device and the cloud.
 

audio_handlers.go

@@ -13,7 +13,7 @@ import (
 
 var audioControlService *audio.AudioControlService
 
-func initAudioControlService() {
+func ensureAudioControlService() *audio.AudioControlService {
 	if audioControlService == nil {
 		sessionProvider := &SessionProviderImpl{}
 		audioControlService = audio.NewAudioControlService(sessionProvider, logger)
@@ -31,50 +31,44 @@ func initAudioControlService() {
 			return nil
 		})
 	}
+	return audioControlService
 }
 
 // --- Global Convenience Functions for Audio Control ---
 
-// StopAudioOutputAndRemoveTracks is a global helper to stop audio output subprocess and remove WebRTC tracks
-func StopAudioOutputAndRemoveTracks() error {
-	initAudioControlService()
-	return audioControlService.MuteAudio(true)
+// MuteAudioOutput is a global helper to mute audio output
+func MuteAudioOutput() error {
+	return ensureAudioControlService().MuteAudio(true)
 }
 
-// StartAudioOutputAndAddTracks is a global helper to start audio output subprocess and add WebRTC tracks
-func StartAudioOutputAndAddTracks() error {
-	initAudioControlService()
-	return audioControlService.MuteAudio(false)
+// UnmuteAudioOutput is a global helper to unmute audio output
+func UnmuteAudioOutput() error {
+	return ensureAudioControlService().MuteAudio(false)
 }
 
-// StopMicrophoneAndRemoveTracks is a global helper to stop microphone subprocess and remove WebRTC tracks
-func StopMicrophoneAndRemoveTracks() error {
-	initAudioControlService()
-	return audioControlService.StopMicrophone()
+// StopMicrophone is a global helper to stop microphone subprocess
+func StopMicrophone() error {
+	return ensureAudioControlService().StopMicrophone()
 }
 
-// StartMicrophoneAndAddTracks is a global helper to start microphone subprocess and add WebRTC tracks
-func StartMicrophoneAndAddTracks() error {
-	initAudioControlService()
-	return audioControlService.StartMicrophone()
+// StartMicrophone is a global helper to start microphone subprocess
+func StartMicrophone() error {
+	return ensureAudioControlService().StartMicrophone()
 }
 
 // IsAudioOutputActive is a global helper to check if audio output subprocess is running
 func IsAudioOutputActive() bool {
-	initAudioControlService()
-	return audioControlService.IsAudioOutputActive()
+	return ensureAudioControlService().IsAudioOutputActive()
 }
 
 // IsMicrophoneActive is a global helper to check if microphone subprocess is running
 func IsMicrophoneActive() bool {
-	initAudioControlService()
-	return audioControlService.IsMicrophoneActive()
+	return ensureAudioControlService().IsMicrophoneActive()
 }
 
 // ResetMicrophone is a global helper to reset the microphone
 func ResetMicrophone() error {
-	initAudioControlService()
-	return audioControlService.ResetMicrophone()
+	return ensureAudioControlService().ResetMicrophone()
 }
 
 // GetCurrentSessionAudioTrack returns the current session's audio track for audio relay
@@ -118,20 +112,20 @@ func ReplaceCurrentSessionAudioTrack(newTrack *webrtc.TrackLocalStaticSample) er
 
 // SetAudioQuality is a global helper to set audio output quality
 func SetAudioQuality(quality audio.AudioQuality) error {
-	initAudioControlService()
+	ensureAudioControlService()
 	audioControlService.SetAudioQuality(quality)
 	return nil
 }
 
 // GetAudioQualityPresets is a global helper to get available audio quality presets
 func GetAudioQualityPresets() map[audio.AudioQuality]audio.AudioConfig {
-	initAudioControlService()
+	ensureAudioControlService()
 	return audioControlService.GetAudioQualityPresets()
 }
 
 // GetCurrentAudioQuality is a global helper to get current audio quality configuration
 func GetCurrentAudioQuality() audio.AudioConfig {
-	initAudioControlService()
+	ensureAudioControlService()
 	return audioControlService.GetCurrentAudioQuality()
 }
 
@@ -148,9 +142,9 @@ func handleAudioMute(c *gin.Context) {
 
 	var err error
 	if req.Muted {
-		err = StopAudioOutputAndRemoveTracks()
+		err = MuteAudioOutput()
 	} else {
-		err = StartAudioOutputAndAddTracks()
+		err = UnmuteAudioOutput()
 	}
 
 	if err != nil {
@@ -166,7 +160,7 @@ func handleAudioMute(c *gin.Context) {
 
 // handleMicrophoneStart handles POST /microphone/start requests
 func handleMicrophoneStart(c *gin.Context) {
-	err := StartMicrophoneAndAddTracks()
+	err := StartMicrophone()
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
 		return
@@ -177,7 +171,7 @@ func handleMicrophoneStart(c *gin.Context) {
 
 // handleMicrophoneStop handles POST /microphone/stop requests
 func handleMicrophoneStop(c *gin.Context) {
-	err := StopMicrophoneAndRemoveTracks()
+	err := StopMicrophone()
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
 		return
@@ -199,9 +193,9 @@ func handleMicrophoneMute(c *gin.Context) {
 
 	var err error
 	if req.Muted {
-		err = StopMicrophoneAndRemoveTracks()
+		err = StopMicrophone()
 	} else {
-		err = StartMicrophoneAndAddTracks()
+		err = StartMicrophone()
 	}
 
 	if err != nil {
@@ -225,19 +219,19 @@ func handleMicrophoneReset(c *gin.Context) {
 
 // handleSubscribeAudioEvents handles WebSocket audio event subscription
 func handleSubscribeAudioEvents(connectionID string, wsCon *websocket.Conn, runCtx context.Context, l *zerolog.Logger) {
-	initAudioControlService()
+	ensureAudioControlService()
 	audioControlService.SubscribeToAudioEvents(connectionID, wsCon, runCtx, l)
 }
 
 // handleUnsubscribeAudioEvents handles WebSocket audio event unsubscription
 func handleUnsubscribeAudioEvents(connectionID string, l *zerolog.Logger) {
-	initAudioControlService()
+	ensureAudioControlService()
 	audioControlService.UnsubscribeFromAudioEvents(connectionID, l)
 }
 
 // handleAudioStatus handles GET requests for audio status
 func handleAudioStatus(c *gin.Context) {
-	initAudioControlService()
+	ensureAudioControlService()
 
 	status := audioControlService.GetAudioStatus()
 	c.JSON(200, status)

cmd/main.go

@@ -11,7 +11,7 @@ import (
 func main() {
 	versionPtr := flag.Bool("version", false, "print version and exit")
 	versionJsonPtr := flag.Bool("version-json", false, "print version as json and exit")
-	audioServerPtr := flag.Bool("audio-output-server", false, "Run as audio server subprocess")
+	audioOutputServerPtr := flag.Bool("audio-output-server", false, "Run as audio server subprocess")
 	audioInputServerPtr := flag.Bool("audio-input-server", false, "Run as audio input server subprocess")
 
 	flag.Parse()
@@ -26,5 +26,5 @@ func main() {
 		return
 	}
 
-	kvm.Main(*audioServerPtr, *audioInputServerPtr)
+	kvm.Main(*audioOutputServerPtr, *audioInputServerPtr)
 }

internal/audio/audio_mute.go

@@ -4,36 +4,35 @@ import (
 	"sync"
 )
 
-var audioMuteState struct {
-	muted bool
-	mu    sync.RWMutex
+// AudioState holds all audio-related state with a single mutex
+type AudioState struct {
+	mu              sync.RWMutex
+	audioMuted      bool
+	microphoneMuted bool
 }
 
-var microphoneMuteState struct {
-	muted bool
-	mu    sync.RWMutex
-}
+var globalAudioState = &AudioState{}
 
 func SetAudioMuted(muted bool) {
-	audioMuteState.mu.Lock()
-	defer audioMuteState.mu.Unlock()
-	audioMuteState.muted = muted
+	globalAudioState.mu.Lock()
+	defer globalAudioState.mu.Unlock()
+	globalAudioState.audioMuted = muted
 }
 
 func IsAudioMuted() bool {
-	audioMuteState.mu.RLock()
-	defer audioMuteState.mu.RUnlock()
-	return audioMuteState.muted
+	globalAudioState.mu.RLock()
+	defer globalAudioState.mu.RUnlock()
+	return globalAudioState.audioMuted
 }
 
 func SetMicrophoneMuted(muted bool) {
-	microphoneMuteState.mu.Lock()
-	defer microphoneMuteState.mu.Unlock()
-	microphoneMuteState.muted = muted
+	globalAudioState.mu.Lock()
+	defer globalAudioState.mu.Unlock()
+	globalAudioState.microphoneMuted = muted
 }
 
 func IsMicrophoneMuted() bool {
-	microphoneMuteState.mu.RLock()
-	defer microphoneMuteState.mu.RUnlock()
-	return microphoneMuteState.muted
+	globalAudioState.mu.RLock()
+	defer globalAudioState.mu.RUnlock()
+	return globalAudioState.microphoneMuted
 }