guh

pi/asound.conf

@@ -17,29 +17,69 @@ pcm.dmixer {
     }
 }
 
-# Software playback volume (adjust with: amixer -c0 sset 'SoftMaster' 70%)
+# TTS volume control (used by default playback path).
-pcm.softvol {
+pcm.tts_softvol {
     type softvol
     slave.pcm "dmixer"
     control {
-        name "SoftMaster"
+        name "TTSMaster"
         card 0
     }
-    min_dB -51.0
+    min_dB -60.0
-    max_dB 0.0
+    max_dB 12.0
 }
 
-# Allow clients with mismatched sample formats/rates to use the mixer.
+# Horn volume control.
-pcm.playback {
+pcm.horn_softvol {
+    type softvol
+    slave.pcm "dmixer"
+    control {
+        name "HornMaster"
+        card 0
+    }
+    min_dB -60.0
+    max_dB 12.0
+}
+
+# Forwarded audio volume control.
+pcm.forward_softvol {
+    type softvol
+    slave.pcm "dmixer"
+    control {
+        name "ForwardMaster"
+        card 0
+    }
+    min_dB -60.0
+    max_dB 12.0
+}
+
+# Per-source playback PCMs.
+pcm.tts {
     type plug
-    slave.pcm "softvol"
+    slave.pcm "tts_softvol"
 }
 
-# Defaults: playback through shared mixer + softvol, capture raw on the HAT
+pcm.horn {
+    type plug
+    slave.pcm "horn_softvol"
+}
+
+pcm.forward {
+    type plug
+    slave.pcm "forward_softvol"
+}
+
+# Capture alias used by rover config defaults.
+pcm.rovermic {
+    type plug
+    slave.pcm "hw:0,0"
+}
+
+# Defaults: TTS direct playback + raw capture on the HAT.
 pcm.!default {
     type asym
-    playback.pcm "playback"
+    playback.pcm "tts"
-    capture.pcm "hw:0,0"
+    capture.pcm "rovermic"
 }
 
 ctl.!default {

pi/bin/audio-forward-listener.sh

@@ -13,7 +13,7 @@ fi
 source "$ENV_FILE"
 
 : "${AUDIO_FORWARD_URL:?AUDIO_FORWARD_URL not set in ${ENV_FILE}}"
-PLAYBACK_DEVICE="${AUDIO_PLAYBACK_DEVICE:-default}"
+PLAYBACK_DEVICE="${AUDIO_PLAYBACK_DEVICE:-forward}"
 
 if [[ -n "${FFMPEG_BIN:-}" ]]; then
   FFMPEG_BIN_PATH="$FFMPEG_BIN"

pi/install_roverd.sh

@@ -223,7 +223,7 @@ AUDIO_FORWARD_URL=srt://192.168.0.86:9000?streamid=#!::r=CHANGE_ME-fwd,m=request
 VIDEO_BITRATE=2000000
 AUDIO_ENABLE=0
 AUDIO_DEVICE=hw:0,0
-AUDIO_PLAYBACK_DEVICE=default
+AUDIO_PLAYBACK_DEVICE=forward
 AUDIO_RATE=48000
 AUDIO_CHANNELS=2
 ENV

pi/roverd/audio_levels.go

@@ -1,5 +1,11 @@
 package roverd
 
+import (
+	"fmt"
+	"math"
+	"os/exec"
+)
+
 type AudioLevels struct {
 	HornGain    float64
 	TTSGain     float64
@@ -34,9 +40,7 @@ func (c *WSClient) setAudioLevels(next AudioLevels) {
 	c.audioMu.Lock()
 	c.audioLevels = normalized
 	c.audioMu.Unlock()
-	if c.horn != nil {
+	c.applyAudioLevelsToMixer(normalized)
-		c.horn.SetGlobalGain(normalized.HornGain)
-	}
 }
 
 func (c *WSClient) handleAudioLevels(payload *audioLevelsPayload) error {
@@ -56,3 +60,35 @@ func (c *WSClient) handleAudioLevels(payload *audioLevelsPayload) error {
 	c.setAudioLevels(levels)
 	return nil
 }
+
+func (c *WSClient) applyAudioLevelsToMixer(levels AudioLevels) {
+	c.applyMixerGain("HornMaster", levels.HornGain)
+	c.applyMixerGain("TTSMaster", levels.TTSGain)
+	c.applyMixerGain("ForwardMaster", levels.ForwardGain)
+}
+
+func (c *WSClient) applyMixerGain(control string, gain float64) {
+	normalized := clampAudioGain(gain)
+	if normalized <= 0 {
+		out, err := exec.Command("amixer", "-q", "-c", "0", "sset", control, "0%").CombinedOutput()
+		if err != nil {
+			c.log.Printf("audio-levels: amixer mute %s failed: %v (%s)", control, err, string(out))
+		}
+		return
+	}
+
+	// Convert linear gain to dB, matching softvol max_dB=12.0 in /etc/asound.conf.
+	db := 20.0 * math.Log10(normalized)
+	if db > 12.0 {
+		db = 12.0
+	}
+	if db < -60.0 {
+		db = -60.0
+	}
+
+	dbArg := fmt.Sprintf("%.2fdB", db)
+	out, err := exec.Command("amixer", "-q", "-c", "0", "sset", control, dbArg).CombinedOutput()
+	if err != nil {
+		c.log.Printf("audio-levels: amixer set %s=%s failed: %v (%s)", control, dbArg, err, string(out))
+	}
+}

pi/roverd/config.go

@@ -172,7 +172,7 @@ func LoadConfig(path string) (*Config, error) {
 		Audio: AudioConfig{
 			CaptureEnabled: false,
 			CaptureDevice:  "rovermic",
-			PlaybackDevice: "default",
+			PlaybackDevice: "forward",
 			SampleRate:     48000,
 			Channels:       2,
 			Bitrate:        24000,
@@ -314,8 +314,8 @@ func validateAudioConfig(cfg *AudioConfig) {
 	if cfg.CaptureEnabled && cfg.CaptureDevice == "" {
 		cfg.CaptureDevice = "hw:0,0"
 	}
-	if cfg.PlaybackDevice == "" {
+	if cfg.PlaybackDevice == "" || cfg.PlaybackDevice == "default" {
-		cfg.PlaybackDevice = "default"
+		cfg.PlaybackDevice = "forward"
 	}
 	if cfg.SampleRate <= 0 {
 		cfg.SampleRate = 48000

pi/roverd/horn.go

@@ -124,10 +124,11 @@ func (h *HornSynth) run(waveform string, freqs []float64, stop <-chan struct{})
 	h.mu.Unlock()
 	volume *= gain
 
-	args := []string{"-q", "-f", "S16_LE", "-c", fmt.Sprintf("%d", channels), "-r", fmt.Sprintf("%d", rate), "-t", "raw"}
+	device := strings.TrimSpace(h.cfg.Device)
-	if h.cfg.Device != "" {
+	if device == "" {
-		args = append(args, "-D", h.cfg.Device)
+		device = "horn"
 	}
+	args := []string{"-q", "-D", device, "-f", "S16_LE", "-c", fmt.Sprintf("%d", channels), "-r", fmt.Sprintf("%d", rate), "-t", "raw"}
 	cmd := exec.Command("aplay", args...)
 	stdin, err := cmd.StdinPipe()
 	if err != nil {

pi/roverd/media_env.go

@@ -54,7 +54,7 @@ func UpdatePublisherEnv(media MediaConfig, audio AudioConfig) error {
 	fmt.Fprintf(&buf, "AUDIO_DEVICE=%s\n", audioDevice)
 	playbackDevice := audio.PlaybackDevice
 	if playbackDevice == "" {
-		playbackDevice = "default"
+		playbackDevice = "forward"
 	}
 	fmt.Fprintf(&buf, "AUDIO_PLAYBACK_DEVICE=%s\n", playbackDevice)
 	fmt.Fprintf(&buf, "AUDIO_RATE=%d\n", audio.SampleRate)

pi/roverd/roverd.sample.yaml

@@ -39,7 +39,7 @@ cameraServo:
 audio:
   captureEnabled: false
   captureDevice: hw:0,0
-  playbackDevice: default
+  playbackDevice: forward
   sampleRate: 48000
   channels: 2
   bitrate: 24000

pi/roverd/tts.go

@@ -3,7 +3,6 @@ package roverd
 import (
 	"context"
 	"fmt"
-	"os"
 	"os/exec"
 	"strings"
 	"time"
@@ -48,75 +47,29 @@ func (c *WSClient) handleTTSPayload(ctx context.Context, payload *ttsPayload) er
 	runCtx, cancel := context.WithTimeout(ctx, 12*time.Second)
 	defer cancel()
 
-	tmp, err := os.CreateTemp("", "roverd-tts-*.wav")
-	if err != nil {
-		return fmt.Errorf("tts temp file: %w", err)
-	}
-	tmpPath := tmp.Name()
-	_ = tmp.Close()
-	defer os.Remove(tmpPath)
-
-	if err := synthTTS(runCtx, engine, voice, pitch, text, tmpPath); err != nil {
-		return err
-	}
-	if err := playTTSFile(runCtx, tmpPath, c.cfg.Audio.PlaybackDevice, c.getAudioLevels().TTSGain); err != nil {
-		return err
-	}
-	return nil
-}
-
-func synthTTS(ctx context.Context, engine, voice string, pitch int, text, outputWavPath string) error {
 	var cmd *exec.Cmd
 	switch engine {
 	case "espeak", "e":
-		args := []string{"-w", outputWavPath}
+		args := []string{}
 		if pitch > 0 {
 			args = append(args, "-p", fmt.Sprintf("%d", pitch))
 		}
 		args = append(args, text)
-		cmd = exec.CommandContext(ctx, "espeak", args...)
+		cmd = exec.CommandContext(runCtx, "espeak", args...)
 	case "flite", "f":
 		args := []string{}
 		if voice != "" {
 			args = append(args, "-voice", voice)
 		}
-		args = append(args, "-t", text, "-o", outputWavPath)
+		args = append(args, "-t", text)
-		cmd = exec.CommandContext(ctx, "flite", args...)
+		cmd = exec.CommandContext(runCtx, "flite", args...)
 	default:
 		return fmt.Errorf("unsupported tts engine: %s", engine)
 	}
 
 	out, err := cmd.CombinedOutput()
 	if err != nil {
-		return fmt.Errorf("tts synth failed: %w (%s)", err, string(out))
+		return fmt.Errorf("tts exec failed: %w (%s)", err, string(out))
-	}
-	return nil
-}
-
-func playTTSFile(ctx context.Context, wavPath, playbackDevice string, gain float64) error {
-	if playbackDevice == "" {
-		playbackDevice = "default"
-	}
-	gain = clampAudioGain(gain)
-	if gain == 0 {
-		// Mute is an explicit value users may choose.
-		return nil
-	}
-
-	args := []string{
-		"-hide_banner",
-		"-loglevel", "warning",
-		"-i", wavPath,
-		"-af", fmt.Sprintf("aresample=16000,volume=%g", gain),
-		"-ac", "1",
-		"-ar", "16000",
-		"-f", "alsa",
-		playbackDevice,
-	}
-	cmd := exec.CommandContext(ctx, "ffmpeg", args...)
-	out, err := cmd.CombinedOutput()
-	if err != nil {
-		return fmt.Errorf("tts playback failed: %w (%s)", err, string(out))
 	}
 	return nil
 }

pi/roverd/wsclient.go

@@ -64,9 +64,7 @@ func NewWSClient(cfg *Config, adapter *SerialAdapter, frames <-chan []byte, even
 			ForwardGain: 1.0,
 		},
 	}
-	if client.horn != nil {
+	client.applyAudioLevelsToMixer(client.audioLevels)
-		client.horn.SetGlobalGain(client.audioLevels.HornGain)
-	}
 	return client
 }