Separate speech capability controls from voice settings (#947)

Move STT/TTS capability toggles to Permissions while keeping speech provider/model/voice setup in Voice & Audio. Disabled voice input now routes users to Permissions; missing speech model setup routes users to Voice & Audio.

Validation: local build; GitHub Build and Test, CodeQL, Socket checks all passed. Live UX proof confirmed disabled STT opens Permissions, missing model opens Voice & Audio, and Voice & Audio setup controls remain available.

Author: calebeden

src/OpenClaw.Tray.WinUI/App.xaml.cs

@@ -2772,8 +2772,8 @@ private void OnGatewayNotificationReceived(object? sender, OpenClawNotification
             //     });
             // }
 
-            // TTS: read response aloud whenever the toggle is on (any chat surface).
-            if (_settings?.VoiceTtsEnabled == true)
+            // TTS: read response aloud whenever chat TTS is enabled and ready (any chat surface).
+            if (SpeechSetupReadiness.IsAutomaticChatTtsEnabled(_settings))
             {
                 _ = (_chatCoordinator?.SpeakResponseAsync(speechText) ?? Task.CompletedTask);
             }

src/OpenClaw.Tray.WinUI/Pages/ChatPage.xaml.cs

@@ -33,6 +33,8 @@ public sealed partial class ChatPage : Page
     private bool _webViewInitialized;
     private bool _webViewMode;
     private bool _pageActive;
+    private readonly SemaphoreSlim _speakerMuteGate = new(1, 1);
+    private int _voiceSettingsDialogOpen;
     private bool _navigationStarted;
     private CancellationTokenSource? _navigationCts;
     private global::Windows.Foundation.TypedEventHandler<CoreWebView2, CoreWebView2NavigationCompletedEventArgs>? _navCompletedHandler;
@@ -232,7 +234,7 @@ private void ShowFunctionalSurface()
 
         var app = App.Current as App;
         var provider = ResolveChatProvider(app);
-        Func<string, Task>? readAloud = app is null ? null : app.SpeakChatTextAsync;
+        Func<string, Task>? readAloud = app is null ? null : ReadChatTextAloudAsync;
 
         // Consume a pending session-key hand-off from SessionsPage or a
         // notification toast so the chat root mounts with that thread selected.
@@ -292,8 +294,8 @@ private void ShowFunctionalSurface()
             onVoiceRequest: VoiceTranscribeAsync,
             onAttachClick: OnAttachClicked,
             onSettingsClick: () => _hub?.NavigateTo("voice"),
-            onSpeakerMuteChanged: muted => (App.Current as App)?.SetChatSpeakerMuted(muted),
-            initialMuted: CurrentApp.Settings?.VoiceTtsEnabled == false,
+            onSpeakerMuteChanged: muted => _ = OnSpeakerMuteChangedAsync(muted),
+            initialMuted: ShouldStartSpeakerMuted(CurrentApp.Settings),
             suppressAutoDispose: true);
         _mountedProvider = provider;
         _mountedThreadId = threadIdToMount;
@@ -829,7 +831,8 @@ private void OnRetryChat(object sender, RoutedEventArgs e)
             await ShowVoiceSettingsDialogAsync(
                 LocalizationHelper.GetString("ChatVoiceDialog_InputOffTitle"),
                 LocalizationHelper.GetString("ChatVoiceDialog_InputOffMessage"),
-                NavigateToVoiceSettings);
+                LocalizationHelper.GetString("ChatVoiceDialog_OpenPermissionsSettings"),
+                NavigateToPermissionsSettings);
             return null;
         }
 
@@ -840,7 +843,8 @@ await ShowVoiceSettingsDialogAsync(
             await ShowVoiceSettingsDialogAsync(
                 LocalizationHelper.GetString("ChatVoiceDialog_InputOffTitle"),
                 LocalizationHelper.GetString("ChatVoiceDialog_InputOffMessage"),
-                NavigateToVoiceSettings);
+                LocalizationHelper.GetString("ChatVoiceDialog_OpenPermissionsSettings"),
+                NavigateToPermissionsSettings);
             return null;
         }
 
@@ -850,6 +854,7 @@ await ShowVoiceSettingsDialogAsync(
             await ShowVoiceSettingsDialogAsync(
                 LocalizationHelper.GetString("ChatVoiceDialog_ModelRequiredTitle"),
                 LocalizationHelper.GetString("ChatVoiceDialog_ModelRequiredMessage"),
+                LocalizationHelper.GetString("ChatVoiceDialog_OpenVoiceSettings"),
                 NavigateToVoiceSettings);
             return null;
         }
@@ -880,8 +885,80 @@ await ShowVoiceSettingsDialogAsync(
         }
     }
 
-    private async Task ShowVoiceSettingsDialogAsync(string title, string message, Action openVoiceSettings)
+    private async Task ReadChatTextAloudAsync(string text)
+    {
+        if (!await EnsureTtsReadyForChatAsync())
+            return;
+
+        await CurrentApp.SpeakChatTextAsync(text);
+    }
+
+    private async Task OnSpeakerMuteChangedAsync(bool muted)
+    {
+        if (!await _speakerMuteGate.WaitAsync(0))
+            return;
+
+        try
+        {
+            if (muted)
+            {
+                (App.Current as App)?.SetChatSpeakerMuted(true);
+                return;
+            }
+
+            if (IsTtsReadyForChat())
+            {
+                (App.Current as App)?.SetChatSpeakerMuted(false);
+                return;
+            }
+
+            (App.Current as App)?.SetChatSpeakerMuted(true);
+            _functionalHost?.SetSpeakerMuted(true);
+            await ShowTtsUnavailableDialogAsync();
+        }
+        catch (Exception ex)
+        {
+            Logger.Warn($"Speaker mute change failed: {ex.Message}");
+        }
+        finally
+        {
+            _speakerMuteGate.Release();
+        }
+    }
+
+    private async Task<bool> EnsureTtsReadyForChatAsync()
+    {
+        if (IsTtsReadyForChat())
+            return true;
+
+        await ShowTtsUnavailableDialogAsync();
+        return false;
+    }
+
+    private static bool IsTtsReadyForChat()
+    {
+        return SpeechSetupReadiness.IsChatTtsPlaybackReady(CurrentApp.Settings);
+    }
+
+    private async Task ShowTtsUnavailableDialogAsync()
+    {
+        await ShowVoiceSettingsDialogAsync(
+            LocalizationHelper.GetString("ChatVoiceDialog_OutputOffTitle"),
+            LocalizationHelper.GetString("ChatVoiceDialog_OutputOffMessage"),
+            LocalizationHelper.GetString("ChatVoiceDialog_OpenPermissionsSettings"),
+            NavigateToPermissionsSettings);
+    }
+
+    private static bool ShouldStartSpeakerMuted(SettingsManager? settings)
+    {
+        return !SpeechSetupReadiness.IsAutomaticChatTtsEnabled(settings);
+    }
+
+    private async Task ShowVoiceSettingsDialogAsync(string title, string message, string primaryButtonText, Action openSettings)
     {
+        if (Interlocked.Exchange(ref _voiceSettingsDialogOpen, 1) == 1)
+            return;
+
         var tcs = new TaskCompletionSource();
         if (DispatcherQueue is null || !DispatcherQueue.TryEnqueue(async () =>
         {
@@ -891,7 +968,7 @@ private async Task ShowVoiceSettingsDialogAsync(string title, string message, Ac
                 {
                     Title = title,
                     Content = message,
-                    PrimaryButtonText = LocalizationHelper.GetString("ChatVoiceDialog_OpenVoiceSettings"),
+                    PrimaryButtonText = primaryButtonText,
                     CloseButtonText = LocalizationHelper.GetString("ChatVoiceDialog_Dismiss"),
                     DefaultButton = ContentDialogButton.Primary,
                     XamlRoot = Content?.XamlRoot
@@ -912,7 +989,7 @@ private async Task ShowVoiceSettingsDialogAsync(string title, string message, Ac
                 };
 
                 if (await dialog.ShowAsync() == ContentDialogResult.Primary)
-                    openVoiceSettings();
+                    openSettings();
             }
             catch (InvalidOperationException ex)
             {
@@ -924,10 +1001,18 @@ private async Task ShowVoiceSettingsDialogAsync(string title, string message, Ac
             }
         }))
         {
+            Interlocked.Exchange(ref _voiceSettingsDialogOpen, 0);
             return;
         }
 
-        await tcs.Task;
+        try
+        {
+            await tcs.Task;
+        }
+        finally
+        {
+            Interlocked.Exchange(ref _voiceSettingsDialogOpen, 0);
+        }
     }
 
     private void NavigateToVoiceSettings()
@@ -938,6 +1023,14 @@ private void NavigateToVoiceSettings()
             (App.Current as App)?.ShowHub("voice");
     }
 
+    private void NavigateToPermissionsSettings()
+    {
+        if (_hub is not null)
+            _hub.NavigateTo("permissions");
+        else
+            (App.Current as App)?.ShowHub("permissions");
+    }
+
     private void OnAttachClicked()
     {
         Logger.Info("[ChatPage] OnAttachClicked invoked");

src/OpenClaw.Tray.WinUI/Pages/PermissionsPage.xaml

@@ -99,61 +99,35 @@
                 </ItemsRepeater.Layout>
             </ItemsRepeater>
 
-            <!-- ═════════ Speech-to-text engine details (only when STT capability is on) ═════════ -->
-            <Border x:Name="SttCard" Background="{ThemeResource SubtleFillColorSecondaryBrush}"
+            <!-- ═════════ Voice settings link (only when STT or TTS capability is on) ═════════ -->
+            <Border x:Name="VoiceSettingsCard" Background="{ThemeResource SubtleFillColorSecondaryBrush}"
                     BorderBrush="{ThemeResource CardStrokeColorDefaultBrush}"
                     BorderThickness="1" CornerRadius="8" Padding="16,10,16,12" Margin="0,-4,0,0"
-                    Visibility="Collapsed">
-                <StackPanel Orientation="Horizontal" Spacing="10">
-                    <FontIcon Glyph="&#xE946;" FontSize="14" VerticalAlignment="Top" Margin="0,3,0,0"
-                              Foreground="{ThemeResource TextFillColorSecondaryBrush}"/>
-                    <StackPanel Spacing="4">
-                        <TextBlock x:Name="SttEngineHint"
+                    Visibility="Collapsed"
+                    AutomationProperties.AutomationId="PermissionsVoiceSettingsCard">
+                <StackPanel Spacing="6">
+                    <StackPanel x:Name="VoiceSettingsHelpPanel"
+                                Orientation="Horizontal"
+                                Spacing="8"
+                                Visibility="Collapsed">
+                        <FontIcon x:Name="VoiceSettingsWarningIcon"
+                                  Glyph="&#xE7BA;"
+                                  FontSize="14"
+                                  Margin="0,1,0,0"
+                                  VerticalAlignment="Top"
+                                  Foreground="{ThemeResource SystemFillColorCautionBrush}"
+                                  AutomationProperties.AccessibilityView="Raw"/>
+                        <TextBlock x:Name="VoiceSettingsHelpText"
+                                   Text=""
                                    Style="{StaticResource CaptionTextBlockStyle}"
-                                   Foreground="{ThemeResource TextFillColorSecondaryBrush}" TextWrapping="Wrap"/>
-                        <HyperlinkButton x:Name="SttMoreSettingsLink"
-                                         x:Uid="PermissionsPage_SttMoreSettingsLink"
-                                         Content="More voice settings…"
-                                         Click="OnSttMoreSettingsClick"
-                                         Padding="0"/>
-                    </StackPanel>
-                </StackPanel>
-            </Border>
-
-            <!-- ═════════ Text-to-speech engine details (only when TTS capability is on) ═════════ -->
-            <Border x:Name="TtsCard" Background="{ThemeResource SubtleFillColorSecondaryBrush}"
-                    BorderBrush="{ThemeResource CardStrokeColorDefaultBrush}"
-                    BorderThickness="1" CornerRadius="8" Padding="16,10,16,12" Margin="0,-4,0,0"
-                    Visibility="Collapsed">
-                <StackPanel Spacing="8">
-                    <ComboBox x:Name="TtsProviderComboBox" x:Uid="PermissionsPage_TtsProviderComboBox" Header="Provider"
-                              SelectionChanged="OnTtsProviderSelectionChanged">
-                        <ComboBoxItem x:Uid="PermissionsPage_TtsProviderPiper" Content="Piper (local ML, recommended)" Tag="piper"/>
-                        <ComboBoxItem x:Uid="PermissionsPage_TtsProviderWindows" Content="Windows built-in speech" Tag="windows"/>
-                        <ComboBoxItem x:Uid="PermissionsPage_TtsProviderElevenLabs" Content="ElevenLabs" Tag="elevenlabs"/>
-                    </ComboBox>
-                    <StackPanel x:Name="TtsElevenLabsPanel" Spacing="6" Visibility="Collapsed">
-                        <PasswordBox x:Name="TtsElevenLabsApiKeyBox"
-                                     x:Uid="PermissionsPage_TtsElevenLabsApiKey"
-                                     Header="ElevenLabs API key"
-                                     LostFocus="OnTtsElevenLabsCommitted"/>
-                        <TextBox x:Name="TtsElevenLabsVoiceIdBox"
-                                 x:Uid="PermissionsPage_TtsElevenLabsVoiceId"
-                                 Header="ElevenLabs voice ID"
-                                 LostFocus="OnTtsElevenLabsCommitted"/>
-                        <TextBox x:Name="TtsElevenLabsModelBox"
-                                 x:Uid="PermissionsPage_TtsElevenLabsModel"
-                                 Header="ElevenLabs model"
-                                 PlaceholderText="eleven_multilingual_v2"
-                                 LostFocus="OnTtsElevenLabsCommitted"/>
-                        <TextBlock x:Uid="PermissionsPage_TtsElevenLabsHelp"
-                                   Text="API key is encrypted at rest with Windows DPAPI. Leave blank to keep the previously saved value when you change other fields."
-                                   Style="{StaticResource CaptionTextBlockStyle}"
-                                   Foreground="{ThemeResource TextFillColorSecondaryBrush}" TextWrapping="Wrap"/>
+                                   Foreground="{ThemeResource TextFillColorSecondaryBrush}"
+                                   TextWrapping="Wrap"/>
                     </StackPanel>
-                    <TextBlock x:Name="TtsStatusText"
-                               Style="{StaticResource CaptionTextBlockStyle}"
-                               Foreground="{ThemeResource TextFillColorSecondaryBrush}"/>
+                    <HyperlinkButton x:Name="VoiceSettingsLink"
+                                     x:Uid="PermissionsPage_VoiceSettingsLink"
+                                     Content="Voice &amp; Audio settings"
+                                     Click="OnVoiceSettingsClick"
+                                     Padding="0"/>
                 </StackPanel>
             </Border>