Talon/voice-cat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(clients): event sound effects + optional text-to-speech

Browse Source 
Add audible cues and optional spoken announcements for session events
(join/leave, channel + PM sent/recv, login, logout/connection-lost,
mic on/off, voice-activity, PTT) across all three clients, driven off
the shared C ABI vc_event stream so the mapping stays consistent.

TTS is off by default; when enabled it announces events and reads
message/PM bodies aloud. Master toggles + a sound-volume slider; the
per-utterance voice-activity and PTT cues default off. WAVs ship from
assets/sounds/.

Windows (built + verified): new VoiceCat.App/Notifications/ layer
(FeedbackSettings -> %AppData%\VoiceCat\feedback.json, SoundPlayerPool
via System.Media.SoundPlayer, SpeechAnnouncer via Prismatoid 0.3.0,
EventFeedback dispatcher); MainForm hooks; NotificationSettingsForm
under Settings > Notifications; csproj adds the Prismatoid PackageRef
and copies the WAVs into sounds\.

macOS + iOS (written, not yet built -- needs a Mac): shared
VoiceCatCore/Feedback/ (SoundEvent, EventFeedback = AVAudioPlayer pool
+ native AVSpeechSynthesizer, FeedbackSettings over UserDefaults); WAVs
bundled via Package.swift resources (.process). Hooks in SessionState/
AppState (iOS) and MainWindowController (macOS); settings UI in
SettingsView (iOS) and SettingsWindowController (macOS).

No core/server code touched; ctest --preset dev unaffected.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Talon
2026-06-22 15:20:11 +02:00
parent 725bd8e925
commit 50416c33a2
45 changed files with 812 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
clients/apple/macOS/VoiceCatMac/Windows/MainWindowController.swift
View File

@@ -35,6 +35,7 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
private var screenAudioSelection: ScreenAudioSelection = .default
internal var pttKeyCode: UInt16 = 0x60 // F8
private var pttMonitor: Any?
private var pttEngaged = false // guards the PTT cue against key-repeat
private var serverMuted = false
private var serverDeafened = false
private var channelTree: [ChannelNode] = []
@@ -343,7 +344,11 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
pttMonitor = NSEvent.addLocalMonitorForEvents(matching: [.keyDown, .keyUp]) { [weak self] event in
guard let self, self.selectedInputMode == .pushToTalk,
self.micStreamId != 0, event.keyCode == self.pttKeyCode else { return event }
self.client.setPushToTalk(event.type == .keyDown)
let down = event.type == .keyDown
self.client.setPushToTalk(down)
// Cue only on the press transition — key-down auto-repeats while held.
if down && !self.pttEngaged { EventFeedback.shared.play(.ptt) }
self.pttEngaged = down
return nil
}
@@ -385,6 +390,8 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
buildMessagesMenu()
buildAdminMenu()
addActivity("Connected to server as \(nickname)")
EventFeedback.shared.play(.login)
EventFeedback.shared.speak("Connected")
}
// MARK: - Event handling
@@ -415,6 +422,8 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
refreshChannelTree(); refreshUserList()
if event.channelId == currentChannelId && event.userId != selfUserId {
addActivity("\(u.nickname) joined the channel")
EventFeedback.shared.play(.channelJoin)
EventFeedback.shared.speak("\(u.nickname) joined")
}
case .userLeft:
@@ -423,7 +432,11 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
users.removeValue(forKey: event.userId)
talkingUsers.remove(event.userId)
refreshChannelTree(); refreshUserList()
if wasHere { addActivity("\(nick) left the channel") }
if wasHere {
addActivity("\(nick) left the channel")
EventFeedback.shared.play(.channelLeave)
EventFeedback.shared.speak("\(nick) left")
}
if let pmWin = pmWindows[event.userId] {
pmWin.appendActivity("\(nick) disconnected from server")
}
@@ -473,6 +486,9 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
let talking = event.u32a == 1
if talking { talkingUsers.insert(event.userId) } else { talkingUsers.remove(event.userId) }
refreshUserList()
if event.userId == selfUserId {
EventFeedback.shared.play(talking ? .vaStart : .vaStop)
}
if talking && event.userId != selfUserId,
let u = users[event.userId], u.channelId == currentChannelId {
addActivity("\(u.nickname) started talking")
@@ -521,21 +537,28 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
time = DateFormatter.localizedString(from: Date(), dateStyle: .none, timeStyle: .short)
}
let sender = nickname(for: event.userId)
let isSelf = event.userId == selfUserId
let body = event.text ?? ""
if event.textScope == .private {
// Route PMs to per-conversation windows. For our own outgoing PM, ev.channelId
// carries the recipient user ID; for incoming, ev.userId is the sender.
let otherId = event.userId == selfUserId ? event.channelId : event.userId
let otherId = isSelf ? event.channelId : event.userId
let win = getOrOpenPmWindow(otherId)
win.appendMessage(time: time, isSelf: event.userId == selfUserId, sender: sender,
text: event.text ?? "")
if event.userId != selfUserId {
win.appendMessage(time: time, isSelf: isSelf, sender: sender, text: body)
EventFeedback.shared.play(isSelf ? .pmSent : .pmRecv)
if !isSelf {
addActivity("Private message from \(sender)")
EventFeedback.shared.speak("Private message from \(sender): \(body)")
}
} else {
let line = "[\(time)] \(sender): \(event.text ?? "")\n"
let line = "[\(time)] \(sender): \(body)\n"
logTextView.textStorage?.append(NSAttributedString(string: line))
logTextView.scrollToEndOfDocument(nil)
EventFeedback.shared.play(isSelf ? .channelSent : .channelRecv)
if !isSelf {
EventFeedback.shared.speak("\(sender): \(body)")
}
}
}
@@ -607,6 +630,8 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
let msg = event.text.map { "Disconnected: \($0)" } ?? "Disconnected from server."
statusLabel.stringValue = msg
addActivity(msg)
EventFeedback.shared.play(event.result == .ok ? .logout : .connectionLost)
EventFeedback.shared.speak(event.result == .ok ? "Disconnected" : "Connection lost")
channelTree = []; channelOutlineView.reloadData()
displayedUsers = []; userTableView.reloadData()
users.removeAll(); talkingUsers.removeAll()
@@ -689,6 +714,7 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
}
setVoiceJoinedState(true)
addActivity("Joined voice — microphone active")
EventFeedback.shared.play(.voiceOn)
NSAccessibility.post(element: logTextView, notification: .announcementRequested,
userInfo: [.announcement: "Joined voice", .priority: NSAccessibilityPriorityLevel.medium])
} else {
@@ -701,6 +727,7 @@ final class MainWindowController: NSWindowController, NSWindowDelegate {
settingsWindowController?.resetLevel()
setVoiceJoinedState(false)
addActivity("Left voice")
EventFeedback.shared.play(.voiceOff)
}
}

70
clients/apple/macOS/VoiceCatMac/Windows/SettingsWindowController.swift
View File

@@ -50,6 +50,21 @@ final class SettingsWindowController: NSWindowController, NSWindowDelegate {
// Cached VAD slider position so we can restore it when the window reopens.
private var vadSliderValue: Double = 50
// Notification feedback controls. Read/write UserDefaults with the same keys VoiceCatCore's
// FeedbackSettings reads, so EventFeedback honours these immediately.
private let soundsCheckbox = NSButton(checkboxWithTitle: "Event sounds", target: nil, action: nil)
private let soundsVolumeSlider: NSSlider = {
let s = NSSlider(value: 1, minValue: 0, maxValue: 1, target: nil, action: nil)
s.numberOfTickMarks = 0
return s
}()
private let speechCheckbox = NSButton(checkboxWithTitle: "Speak events (text-to-speech)",
target: nil, action: nil)
private let selfTalkCheckbox = NSButton(checkboxWithTitle: "Your own voice-activity sounds",
target: nil, action: nil)
private let pttSoundCheckbox = NSButton(checkboxWithTitle: "Push-to-talk cue",
target: nil, action: nil)
// MARK: - Init
init(client: VoiceCatClient, mainController: MainWindowController) {
@@ -57,13 +72,13 @@ final class SettingsWindowController: NSWindowController, NSWindowDelegate {
self.mainController = mainController
let window = NSWindow(
contentRect: NSRect(x: 0, y: 0, width: 380, height: 260),
contentRect: NSRect(x: 0, y: 0, width: 380, height: 420),
styleMask: [.titled, .closable, .miniaturizable],
backing: .buffered,
defer: false
)
window.title = "Audio Settings"
window.minSize = NSSize(width: 340, height: 220)
window.title = "Settings"
window.minSize = NSSize(width: 340, height: 380)
window.center()
super.init(window: window)
window.delegate = self
@@ -140,7 +155,31 @@ final class SettingsWindowController: NSWindowController, NSWindowDelegate {
levelRow.orientation = .horizontal
levelRow.spacing = 8
let stack = NSStackView(views: [inputModeRow, vadRow, pttRow, deviceRow, levelRow])
// Notifications
let notificationsHeader = NSTextField(labelWithString: "Notifications")
notificationsHeader.font = .boldSystemFont(ofSize: NSFont.systemFontSize)
for box in [soundsCheckbox, speechCheckbox, selfTalkCheckbox, pttSoundCheckbox] {
box.target = self
box.action = #selector(notificationSettingChanged)
}
soundsCheckbox.setAccessibilityLabel("Play event sounds")
speechCheckbox.setAccessibilityLabel("Speak events")
selfTalkCheckbox.setAccessibilityLabel("Your own voice-activity sounds")
pttSoundCheckbox.setAccessibilityLabel("Push-to-talk cue")
let volumeLabel = NSTextField(labelWithString: "Sound volume:")
volumeLabel.setAccessibilityLabel("Sound volume")
soundsVolumeSlider.target = self
soundsVolumeSlider.action = #selector(notificationSettingChanged)
soundsVolumeSlider.setAccessibilityLabel("Sound volume")
let volumeRow = NSStackView(views: [volumeLabel, soundsVolumeSlider])
volumeRow.orientation = .horizontal
volumeRow.spacing = 8
let stack = NSStackView(views: [inputModeRow, vadRow, pttRow, deviceRow, levelRow,
notificationsHeader, soundsCheckbox, volumeRow,
speechCheckbox, selfTalkCheckbox, pttSoundCheckbox])
stack.orientation = .vertical
stack.spacing = 12
stack.alignment = .leading
@@ -157,7 +196,30 @@ final class SettingsWindowController: NSWindowController, NSWindowDelegate {
vadSlider.widthAnchor.constraint(greaterThanOrEqualToConstant: 200),
levelMeter.widthAnchor.constraint(equalToConstant: 200),
devicePicker.widthAnchor.constraint(greaterThanOrEqualToConstant: 180),
soundsVolumeSlider.widthAnchor.constraint(greaterThanOrEqualToConstant: 200),
])
syncNotificationControls()
}
/// Load the notification checkbox/slider states from UserDefaults. Touches EventFeedback.shared
/// first so its default values are registered before we read them.
private func syncNotificationControls() {
let s = FeedbackSettings.current
soundsCheckbox.state = s.sounds ? .on : .off
speechCheckbox.state = s.speech ? .on : .off
selfTalkCheckbox.state = s.selfTalkSounds ? .on : .off
pttSoundCheckbox.state = s.pttSound ? .on : .off
soundsVolumeSlider.doubleValue = Double(s.volume)
}
@objc private func notificationSettingChanged() {
let d = UserDefaults.standard
d.set(soundsCheckbox.state == .on, forKey: "feedback.sounds")
d.set(speechCheckbox.state == .on, forKey: "feedback.speech")
d.set(selfTalkCheckbox.state == .on, forKey: "feedback.selfTalk")
d.set(pttSoundCheckbox.state == .on, forKey: "feedback.ptt")
d.set(soundsVolumeSlider.doubleValue, forKey: "feedback.volume")
}
// MARK: - Sync from MainWindowController