feat(voice): implement real-time voice mode with cloud and local backends (#24174)

This commit is contained in:
Abhijit Balaji
2026-04-24 14:29:38 -07:00
committed by GitHub
parent 048bf6e514
commit 2e0641c83b
40 changed files with 2244 additions and 43 deletions
+24
View File
@@ -103,6 +103,7 @@ import { useQuotaAndFallback } from './hooks/useQuotaAndFallback.js';
import { useEditorSettings } from './hooks/useEditorSettings.js';
import { useSettingsCommand } from './hooks/useSettingsCommand.js';
import { useModelCommand } from './hooks/useModelCommand.js';
import { useVoiceModelCommand } from './hooks/useVoiceModelCommand.js';
import { useSlashCommandProcessor } from './hooks/slashCommandProcessor.js';
import { useVimMode } from './contexts/VimModeContext.js';
import {
@@ -312,6 +313,7 @@ export const AppContainer = (props: AppContainerProps) => {
);
const [shellModeActive, setShellModeActive] = useState(false);
const [isVoiceModeEnabled, setVoiceModeEnabled] = useState(false);
const [modelSwitchedFromQuotaError, setModelSwitchedFromQuotaError] =
useState<boolean>(false);
const [historyRemountKey, setHistoryRemountKey] = useState(0);
@@ -946,6 +948,12 @@ Logging in with Google... Restarting Gemini CLI to continue.
const { isModelDialogOpen, openModelDialog, closeModelDialog } =
useModelCommand();
const {
isVoiceModelDialogOpen,
openVoiceModelDialog,
closeVoiceModelDialog,
} = useVoiceModelCommand();
const { toggleVimEnabled } = useVimMode();
const setIsBackgroundTaskListOpenRef = useRef<(open: boolean) => void>(
@@ -969,6 +977,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
openSettingsDialog,
openSessionBrowser,
openModelDialog,
openVoiceModelDialog,
openAgentConfigDialog,
openPermissionsDialog,
quit: (messages: HistoryItem[]) => {
@@ -981,6 +990,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
},
setDebugMessage,
toggleCorgiMode: () => setCorgiMode((prev) => !prev),
toggleVoiceMode: () => setVoiceModeEnabled((prev) => !prev),
toggleDebugProfiler,
dispatchExtensionStateUpdate,
addConfirmUpdateExtensionRequest,
@@ -1006,6 +1016,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
openSettingsDialog,
openSessionBrowser,
openModelDialog,
openVoiceModelDialog,
openAgentConfigDialog,
setQuittingMessages,
setDebugMessage,
@@ -2191,6 +2202,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
isThemeDialogOpen ||
isSettingsDialogOpen ||
isModelDialogOpen ||
isVoiceModelDialogOpen ||
isAgentConfigDialogOpen ||
isPermissionsDialogOpen ||
isAuthenticating ||
@@ -2448,6 +2460,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
isSettingsDialogOpen,
isSessionBrowserOpen,
isModelDialogOpen,
isVoiceModelDialogOpen,
isAgentConfigDialogOpen,
selectedAgentName,
selectedAgentDisplayName,
@@ -2468,6 +2481,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
pendingGeminiHistoryItems,
thought,
isInputActive,
isVoiceModeEnabled,
isResuming,
shouldShowIdePrompt,
isFolderTrustDialogOpen: isFolderTrustDialogOpen ?? false,
@@ -2559,6 +2573,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
isSettingsDialogOpen,
isSessionBrowserOpen,
isModelDialogOpen,
isVoiceModelDialogOpen,
isAgentConfigDialogOpen,
selectedAgentName,
selectedAgentDisplayName,
@@ -2579,6 +2594,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
pendingGeminiHistoryItems,
thought,
isInputActive,
isVoiceModeEnabled,
isResuming,
shouldShowIdePrompt,
isFolderTrustDialogOpen,
@@ -2671,6 +2687,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
exitPrivacyNotice,
closeSettingsDialog,
closeModelDialog,
openVoiceModelDialog,
closeVoiceModelDialog,
openAgentConfigDialog,
closeAgentConfigDialog,
openPermissionsDialog,
@@ -2751,6 +2769,9 @@ Logging in with Google... Restarting Gemini CLI to continue.
setAccountSuspensionInfo(null);
setAuthState(AuthState.Updating);
},
setVoiceModeEnabled: (value: boolean) => {
setVoiceModeEnabled(value);
},
}),
[
handleThemeSelect,
@@ -2764,6 +2785,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
exitPrivacyNotice,
closeSettingsDialog,
closeModelDialog,
openVoiceModelDialog,
closeVoiceModelDialog,
openAgentConfigDialog,
closeAgentConfigDialog,
openPermissionsDialog,
@@ -2807,6 +2830,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
config,
historyManager,
getPreferredEditor,
setVoiceModeEnabled,
],
);