legop3/MultiRoombaRover
1
0
Fork 0
mirror of https://github.com/legop3/MultiRoombaRover.git synced 2026-09-16 09:31:20 -04:00
Code Issues Actions Packages Projects Releases Wiki Activity

audio

Browse Source
This commit is contained in:
legop3
2026-03-16 21:30:56 -04:00
parent 4aa53e8f80
commit aaa93847e1
20 changed files with 567 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pi/roverd/audio_levels.go
+58
View File
@@ -0,0 +1,58 @@
package roverd
type AudioLevels struct {
HornGain float64
TTSGain float64
ForwardGain float64
}
func clampAudioGain(v float64) float64 {
if v < 0 {
return 0
}
if v > 4 {
return 4
}
return v
}
func normalizeAudioLevels(v AudioLevels) AudioLevels {
v.HornGain = clampAudioGain(v.HornGain)
v.TTSGain = clampAudioGain(v.TTSGain)
v.ForwardGain = clampAudioGain(v.ForwardGain)
return v
}
func (c *WSClient) getAudioLevels() AudioLevels {
c.audioMu.RLock()
defer c.audioMu.RUnlock()
return c.audioLevels
}
func (c *WSClient) setAudioLevels(next AudioLevels) {
normalized := normalizeAudioLevels(next)
c.audioMu.Lock()
c.audioLevels = normalized
c.audioMu.Unlock()
if c.horn != nil {
c.horn.SetGlobalGain(normalized.HornGain)
}
}
func (c *WSClient) handleAudioLevels(payload *audioLevelsPayload) error {
if payload == nil {
return nil
}
levels := c.getAudioLevels()
if payload.HornGain != nil {
levels.HornGain = clampAudioGain(*payload.HornGain)
}
if payload.TTSGain != nil {
levels.TTSGain = clampAudioGain(*payload.TTSGain)
}
if payload.ForwardGain != nil {
levels.ForwardGain = clampAudioGain(*payload.ForwardGain)
}
c.setAudioLevels(levels)
return nil
}
pi/roverd/command.go
+7
View File
@@ -29,6 +29,7 @@ type inboundMessage struct {
Servo *servoPayload `json:"servo,omitempty"`
TTS *ttsPayload `json:"tts,omitempty"`
Horn *hornPayload `json:"horn,omitempty"`
AudioLevels *audioLevelsPayload `json:"audioLevels,omitempty"`
NightVision *nightVisionPayload `json:"nightVision,omitempty"`
Song *songPayload `json:"song,omitempty"`
Reboot *rebootPayload `json:"reboot,omitempty"`
@@ -73,6 +74,12 @@ type hornPayload struct {
Freqs []float64 `json:"freqs,omitempty"`
}
type audioLevelsPayload struct {
HornGain *float64 `json:"hornGain,omitempty"`
TTSGain *float64 `json:"ttsGain,omitempty"`
ForwardGain *float64 `json:"forwardGain,omitempty"`
}
type nightVisionPayload struct {
Action string `json:"action"`
}
pi/roverd/horn.go
+16 -4
View File
@@ -18,8 +18,9 @@ const (
)
type HornSynth struct {
cfg HornConfig
log *log.Logger
cfg HornConfig
log *log.Logger
gain float64
mu sync.Mutex
stop chan struct{}
@@ -29,11 +30,18 @@ type HornSynth struct {
func NewHornSynth(cfg HornConfig, logger *log.Logger) *HornSynth {
return &HornSynth{
cfg: cfg,
log: logger,
cfg: cfg,
log: logger,
gain: 1.0,
}
}
func (h *HornSynth) SetGlobalGain(gain float64) {
h.mu.Lock()
defer h.mu.Unlock()
h.gain = clampAudioGain(gain)
}
func (h *HornSynth) HandlePayload(payload *hornPayload) error {
if payload == nil {
return fmt.Errorf("horn payload required")
@@ -111,6 +119,10 @@ func (h *HornSynth) run(waveform string, freqs []float64, stop <-chan struct{})
if volume > 1 {
volume = 1
}
h.mu.Lock()
gain := h.gain
h.mu.Unlock()
volume *= gain
args := []string{"-q", "-f", "S16_LE", "-c", fmt.Sprintf("%d", channels), "-r", fmt.Sprintf("%d", rate), "-t", "raw"}
if h.cfg.Device != "" {
pi/roverd/tts.go
+52 -5
View File
@@ -3,6 +3,7 @@ package roverd
import (
"context"
"fmt"
"os"
"os/exec"
"strings"
"time"
@@ -47,29 +48,75 @@ 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{}
args := []string{"-w", outputWavPath}
if pitch > 0 {
args = append(args, "-p", fmt.Sprintf("%d", pitch))
}
args = append(args, text)
cmd = exec.CommandContext(runCtx, "espeak", args...)
cmd = exec.CommandContext(ctx, "espeak", args...)
case "flite", "f":
args := []string{}
if voice != "" {
args = append(args, "-voice", voice)
}
args = append(args, "-t", text)
cmd = exec.CommandContext(runCtx, "flite", args...)
args = append(args, "-t", text, "-o", outputWavPath)
cmd = exec.CommandContext(ctx, "flite", args...)
default:
return fmt.Errorf("unsupported tts engine: %s", engine)
}
out, err := cmd.CombinedOutput()
if err != nil {
return fmt.Errorf("tts exec failed: %w (%s)", err, string(out))
return fmt.Errorf("tts synth 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
+14 -1
View File
@@ -34,6 +34,8 @@ type WSClient struct {
rebootT *time.Timer
seekIssued bool
rebootIssued bool
audioLevels AudioLevels
audioMu sync.RWMutex
}
func NewWSClient(cfg *Config, adapter *SerialAdapter, frames <-chan []byte, events chan RoverEvent, media *MediaSupervisor, servo *CameraServo, nightVision *NightVisionLight, logger *log.Logger) *WSClient {
@@ -45,7 +47,7 @@ func NewWSClient(cfg *Config, adapter *SerialAdapter, frames <-chan []byte, even
if cfg.Horn.Enabled {
horn = NewHornSynth(cfg.Horn, logger)
}
return &WSClient{
client := &WSClient{
cfg: cfg,
adapter: adapter,
sensorFrames: frames,
@@ -56,7 +58,16 @@ func NewWSClient(cfg *Config, adapter *SerialAdapter, frames <-chan []byte, even
nightVision: nightVision,
log: logger,
ttsQueue: ttsQueue,
audioLevels: AudioLevels{
HornGain: 1.0,
TTSGain: 1.0,
ForwardGain: 1.0,
},
}
if client.horn != nil {
client.horn.SetGlobalGain(client.audioLevels.HornGain)
}
return client
}
func (c *WSClient) Run(ctx context.Context) error {
@@ -200,6 +211,8 @@ func (c *WSClient) dispatch(ctx context.Context, msg *inboundMessage) error {
return fmt.Errorf("horn disabled")
}
return c.horn.HandlePayload(msg.Horn)
case msg.AudioLevels != nil:
return c.handleAudioLevels(msg.AudioLevels)
case msg.NightVision != nil:
if c.nightVision == nil {
return fmt.Errorf("night vision disabled")