MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-05-14 22:02:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

feat(voice): add privacy and compliance UX warning for Gemini Live backend (#26454)

Browse Source
This commit is contained in:
Coco Sheng
2026-05-04 14:32:15 -04:00
committed by GitHub
parent d313cd7dde
commit 60a6a47d56
6 changed files with 126 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cli/settings.md
+1 -1
View File
@@ -166,7 +166,7 @@ they appear in the UI.
| Gemma Models | `experimental.gemma` | Enable access to Gemma 4 models via Gemini API. | `true` |
| Voice Mode | `experimental.voiceMode` | Enable experimental voice dictation and commands (/voice, /voice model). | `false` |
| Voice Activation Mode | `experimental.voice.activationMode` | How to trigger voice recording with the Space key. | `"push-to-talk"` |
| Voice Transcription Backend | `experimental.voice.backend` | The backend to use for voice transcription. | `"gemini-live"` |
| Voice Transcription Backend | `experimental.voice.backend` | The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription. | `"gemini-live"` |
| Whisper Model | `experimental.voice.whisperModel` | The Whisper model to use for local transcription. | `"ggml-base.en.bin"` |
| Voice Stop Grace Period (ms) | `experimental.voice.stopGracePeriodMs` | How long to wait for final transcription after stopping recording. | `1000` |
| Enable Git Worktrees | `experimental.worktrees` | Enable automated Git worktree management for parallel work. | `false` |
docs/reference/configuration.md
+3 -1
View File
@@ -1774,7 +1774,9 @@ their corresponding top-level category object in your `settings.json` file.
- **Values:** `"push-to-talk"`, `"toggle"`
- **`experimental.voice.backend`** (enum):
- **Description:** The backend to use for voice transcription.
- **Description:** The backend to use for voice transcription. Note: When
using the Gemini Live backend, voice recordings are sent to Google Cloud for
transcription.
- **Default:** `"gemini-live"`
- **Values:** `"gemini-live"`, `"whisper"`
packages/cli/src/config/settingsSchema.ts
+5 -1
View File
@@ -2099,7 +2099,11 @@ const SETTINGS_SCHEMA = {
category: 'Experimental',
requiresRestart: false,
default: 'gemini-live',
description: 'The backend to use for voice transcription.',
description: oneLine`
The backend to use for voice transcription. Note: When using the
Gemini Live backend, voice recordings are sent to Google Cloud for
transcription.
`,
showInDialog: true,
options: [
{ value: 'gemini-live', label: 'Gemini Live API (Cloud)' },
packages/cli/src/ui/components/VoiceModelDialog.test.tsx
+92
View File
@@ -0,0 +1,92 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
import { describe, it, expect, vi } from 'vitest';
import { renderWithProviders } from '../../test-utils/render.js';
import { createMockSettings } from '../../test-utils/settings.js';
import { VoiceModelDialog } from './VoiceModelDialog.js';
import { act } from 'react';
import { waitFor } from '../../test-utils/async.js';
import { SettingScope } from '../../config/settings.js';
vi.mock('@google/gemini-cli-core', async () => {
const actual = await vi.importActual('@google/gemini-cli-core');
return {
...actual,
isBinaryAvailable: vi.fn().mockReturnValue(true),
WhisperModelManager: vi.fn().mockImplementation(() => ({
isModelInstalled: vi.fn().mockReturnValue(false),
on: vi.fn(),
off: vi.fn(),
downloadModel: vi.fn(),
})),
};
});
describe('VoiceModelDialog', () => {
it('should display a privacy warning when Gemini Live API (Cloud) is selected', async () => {
const onClose = vi.fn();
const { lastFrame, waitUntilReady } = await renderWithProviders(
<VoiceModelDialog onClose={onClose} />,
);
await waitUntilReady();
const frame = lastFrame();
expect(frame).toContain('Gemini Live API (Cloud)');
expect(frame).toContain('When using the Gemini Live backend');
});
it('should NOT display a privacy warning when Whisper (Local) is highlighted', async () => {
const onClose = vi.fn();
const { lastFrame, waitUntilReady, stdin } = await renderWithProviders(
<VoiceModelDialog onClose={onClose} />,
);
await waitUntilReady();
// Verify warning is present for default (Gemini Live)
expect(lastFrame()).toContain('When using the Gemini Live backend');
// Arrow Down to highlight Whisper
await act(async () => {
stdin.write('\u001b[B');
});
await waitFor(() => {
const frame = lastFrame();
expect(frame).toContain('Whisper (Local)');
expect(frame).not.toContain('When using the Gemini Live backend');
});
});
it('should update settings and close dialog when a backend is selected', async () => {
const onClose = vi.fn();
const settings = createMockSettings();
const setValueSpy = vi.spyOn(settings, 'setValue');
const { waitUntilReady, stdin } = await renderWithProviders(
<VoiceModelDialog onClose={onClose} />,
{ settings },
);
await waitUntilReady();
// Select Gemini Live (it's already highlighted, just press Enter)
await act(async () => {
stdin.write('\r');
});
await waitFor(() => {
expect(setValueSpy).toHaveBeenCalledWith(
SettingScope.User,
'experimental.voice.backend',
'gemini-live',
);
expect(onClose).toHaveBeenCalled();
});
});
});
packages/cli/src/ui/components/VoiceModelDialog.tsx
+23 -7
View File
@@ -18,6 +18,7 @@ import {
type WhisperModelProgress,
} from '@google/gemini-cli-core';
import { CliSpinner } from './CliSpinner.js';
import { WarningMessage } from './messages/WarningMessage.js';
interface VoiceModelDialogProps {
onClose: () => void;
@@ -68,6 +69,9 @@ export function VoiceModelDialog({
const currentWhisperModel =
settings.merged.experimental.voice?.whisperModel ?? 'ggml-base.en.bin';
const [highlightedBackend, setHighlightedBackend] =
useState<string>(currentBackend);
const handleKeypress = useCallback(
(key: Key) => {
if (key.name === 'escape') {
@@ -101,6 +105,10 @@ export function VoiceModelDialog({
[setSetting, onClose],
);
const handleBackendHighlight = useCallback((value: string) => {
setHighlightedBackend(value);
}, []);
const handleWhisperModelSelect = useCallback(
async (modelName: string) => {
if (modelManager.isModelInstalled(modelName)) {
@@ -203,14 +211,22 @@ export function VoiceModelDialog({
</Box>
</Box>
) : (
<Box marginTop={1}>
<Box marginTop={1} flexDirection="column">
{view === 'backend' ? (
<DescriptiveRadioButtonSelect
items={backendOptions}
onSelect={handleBackendSelect}
initialIndex={currentBackend === 'whisper' ? 1 : 0}
showNumbers={true}
/>
<>
<DescriptiveRadioButtonSelect
items={backendOptions}
onSelect={handleBackendSelect}
onHighlight={handleBackendHighlight}
initialIndex={currentBackend === 'whisper' ? 1 : 0}
showNumbers={true}
/>
{highlightedBackend === 'gemini-live' && (
<Box marginTop={1}>
<WarningMessage text="When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription. Enterprise users should verify this aligns with their data privacy and compliance requirements." />
</Box>
)}
</>
) : (
<DescriptiveRadioButtonSelect
items={whisperOptions}
schemas/settings.schema.json
+2 -2
View File
@@ -3078,8 +3078,8 @@
},
"backend": {
"title": "Voice Transcription Backend",
"description": "The backend to use for voice transcription.",
"markdownDescription": "The backend to use for voice transcription.\n\n- Category: `Experimental`\n- Requires restart: `no`\n- Default: `gemini-live`",
"description": "The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription.",
"markdownDescription": "The backend to use for voice transcription. Note: When using the Gemini Live backend, voice recordings are sent to Google Cloud for transcription.\n\n- Category: `Experimental`\n- Requires restart: `no`\n- Default: `gemini-live`",
"default": "gemini-live",
"type": "string",
"enum": ["gemini-live", "whisper"]