mirror of
https://github.com/openclaw/openclaw.git
synced 2026-04-03 13:22:14 +00:00
350fe63bbf
* feat(macos): add "Trigger Talk Mode" option to Voice Wake settings When enabled, detecting a wake phrase activates Talk Mode (full voice conversation: STT -> LLM -> TTS playback) instead of sending a text message to the chat. Enables hands-free voice assistant UX. Implementation: - Constants.swift: new `openclaw.voiceWakeTriggersTalkMode` defaults key - AppState.swift: new property with UserDefaults persistence + runtime refresh on change so the toggle takes effect immediately - VoiceWakeSettings.swift: "Trigger Talk Mode" toggle under Voice Wake, disabled when Voice Wake is off - VoiceWakeRuntime.swift: `beginCapture` checks `triggersTalkMode` and activates Talk Mode directly, skipping the capture/overlay/forward flow. Pauses the wake listener via `pauseForPushToTalk()` to prevent two audio pipelines competing on the mic. - TalkModeController.swift: resumes voice wake listener when Talk Mode exits by calling `VoiceWakeRuntime.refresh`, mirroring PTT teardown. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address review feedback - TalkModeController: move VoiceWakeRuntime.refresh() after TalkModeRuntime.setEnabled(false) completes, preventing mic contention race where wake listener restarts before Talk Mode finishes tearing down its audio engine (P1) - VoiceWakeRuntime: remove redundant haltRecognitionPipeline() before pauseForPushToTalk() which already calls it via stop() (P2) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: resume wake listener based on enabled state, not toggle value Check swabbleEnabled instead of voiceWakeTriggersTalkMode when deciding whether to resume the wake listener after Talk Mode exits. This ensures the paused listener resumes even if the user toggled "Trigger Talk Mode" off during an active session. (P2) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: play trigger chime on Talk Mode activation + send chime before TTS - VoiceWakeRuntime: play the configured trigger chime in the triggersTalkMode branch before pausing the wake listener. The early return was skipping the chime that plays in the normal capture flow. - TalkModeRuntime: play the Voice Wake "send" chime before TTS playback starts, giving audible feedback that the AI is about to respond. Talk Mode never used this chime despite it being configurable in settings. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: move send chime to transcript finalization (on send, not on reply) The send chime now plays when the user's speech is finalized and about to be sent to the AI, not when the TTS response starts. This matches the semantics of "send sound" -- it confirms your input was captured. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
76 lines
2.4 KiB
Swift
76 lines
2.4 KiB
Swift
import Observation
|
|
|
|
@MainActor
|
|
@Observable
|
|
final class TalkModeController {
|
|
static let shared = TalkModeController()
|
|
|
|
private let logger = Logger(subsystem: "ai.openclaw", category: "talk.controller")
|
|
|
|
private(set) var phase: TalkModePhase = .idle
|
|
private(set) var isPaused: Bool = false
|
|
|
|
func setEnabled(_ enabled: Bool) async {
|
|
self.logger.info("talk enabled=\(enabled)")
|
|
if enabled {
|
|
TalkOverlayController.shared.present()
|
|
} else {
|
|
TalkOverlayController.shared.dismiss()
|
|
}
|
|
await TalkModeRuntime.shared.setEnabled(enabled)
|
|
// Resume voice wake listener *after* TalkMode audio is fully torn down.
|
|
// Check swabbleEnabled (not voiceWakeTriggersTalkMode) so the paused wake listener
|
|
// resumes even if the user toggled "Trigger Talk Mode" off during the session.
|
|
if !enabled, AppStateStore.shared.swabbleEnabled {
|
|
Task { await VoiceWakeRuntime.shared.refresh(state: AppStateStore.shared) }
|
|
}
|
|
}
|
|
|
|
func updatePhase(_ phase: TalkModePhase) {
|
|
self.phase = phase
|
|
TalkOverlayController.shared.updatePhase(phase)
|
|
let effectivePhase = self.isPaused ? "paused" : phase.rawValue
|
|
Task {
|
|
await GatewayConnection.shared.talkMode(
|
|
enabled: AppStateStore.shared.talkEnabled,
|
|
phase: effectivePhase)
|
|
}
|
|
}
|
|
|
|
func updateLevel(_ level: Double) {
|
|
TalkOverlayController.shared.updateLevel(level)
|
|
}
|
|
|
|
func setPaused(_ paused: Bool) {
|
|
guard self.isPaused != paused else { return }
|
|
self.logger.info("talk paused=\(paused)")
|
|
self.isPaused = paused
|
|
TalkOverlayController.shared.updatePaused(paused)
|
|
let effectivePhase = paused ? "paused" : self.phase.rawValue
|
|
Task {
|
|
await GatewayConnection.shared.talkMode(
|
|
enabled: AppStateStore.shared.talkEnabled,
|
|
phase: effectivePhase)
|
|
}
|
|
Task { await TalkModeRuntime.shared.setPaused(paused) }
|
|
}
|
|
|
|
func togglePaused() {
|
|
self.setPaused(!self.isPaused)
|
|
}
|
|
|
|
func stopSpeaking(reason: TalkStopReason = .userTap) {
|
|
Task { await TalkModeRuntime.shared.stopSpeaking(reason: reason) }
|
|
}
|
|
|
|
func exitTalkMode() {
|
|
Task { await AppStateStore.shared.setTalkEnabled(false) }
|
|
}
|
|
}
|
|
|
|
enum TalkStopReason {
|
|
case userTap
|
|
case speech
|
|
case manual
|
|
}
|