Skip to content

Add system-wide dictation for Pro users #7652

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ComputelessComputer merged 4 commits into from
Sep 17, 2026
Merged

Add system-wide dictation for Pro users #7652

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ae2919a
Add system-wide dictation for Pro users
ComputelessComputer Sep 16, 2026
06ad270
Harden dictation cancellation and native input handling
ComputelessComputer Sep 17, 2026
de332e7
Keep the last dictation through shortcut reconfiguration
ComputelessComputer Sep 17, 2026
018ca42
Translate dictation settings into Spanish
ComputelessComputer Sep 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 61 additions & 0 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions apps/desktop/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
"@anlg/plugin-deeplink2": "workspace:*",
"@anlg/plugin-detect": "workspace:*",
"@anlg/plugin-dictation": "workspace:*",
"@anlg/plugin-shortcut": "workspace:*",
"@anlg/plugin-export": "workspace:*",
"@anlg/plugin-fs-sync": "workspace:*",
"@anlg/plugin-fs2": "workspace:*",
Expand Down
22 changes: 22 additions & 0 deletions apps/desktop/public/dictation.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
<!doctype html>
<html lang="en">
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Anarlog Dictation</title>
<style>
html, body { margin: 0; width: 100%; height: 100%; background: #191919; color: white; font: 14px system-ui; }
body { display: flex; align-items: center; justify-content: center; gap: 12px; }
.light { width: 10px; height: 10px; border-radius: 50%; background: #ff5757; animation: pulse 1s infinite alternate; }
.processing { display: none; }
[data-phase="processing"] .recording { display: none; }
[data-phase="processing"] .processing { display: inline; }
[data-phase="processing"] .light { background: #aaa; }
@keyframes pulse { to { opacity: 0.45; } }
@media (prefers-reduced-motion: reduce) { .light { animation: none; } }
</style>
<body data-phase="recording">
<span class="light"></span>
<span class="recording">Listening…</span>
<span class="processing">Transcribing…</span>
</body>
</html>
3 changes: 2 additions & 1 deletion apps/desktop/src-tauri/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -345,7 +345,7 @@ pub fn main() {
.plugin(
tauri_plugin_window_state::Builder::default()
.with_state_flags(tauri_plugin_windows::persisted_window_state_flags())
.with_denylist(&["composer"])
.with_denylist(&["composer", "dictation-overlay"])
.build(),
)
.plugin(tauri_plugin_transcription::init())
Expand Down Expand Up @@ -397,6 +397,7 @@ pub fn main() {
.on_window_event(tauri_plugin_windows::on_window_event)
.setup(move |app| {
let app_handle = app.handle().clone();
tauri_plugin_shortcut::initialize_global_shortcuts(&app_handle);

specta_builder.mount_events(&app_handle);

Expand Down
5 changes: 4 additions & 1 deletion apps/desktop/src/chat/components/input/use-dictation.test.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,10 @@ describe("useDictation", () => {
await result.current.start();
});
expect(result.current.phase).toBe("recording");
expect(mocks.startRecording).toHaveBeenCalledWith("Built-in Microphone");
expect(mocks.startRecording).toHaveBeenCalledWith(
"Built-in Microphone",
mocks.useRunBatch.mock.calls[0][0],
);

await act(async () => {
await result.current.stop();
Expand Down
35 changes: 27 additions & 8 deletions apps/desktop/src/chat/components/input/use-dictation.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,12 +70,13 @@ export function useDictation({

const result = await dictationCommands.startRecording(
microphoneDevice || null,
transcriptionSessionId,
);
if (result.status === "error") {
throw new Error(result.error);
}
if (!mountedRef.current) {
await cancelActiveRecording();
await cancelActiveRecording(transcriptionSessionId);
return;
}

Expand All @@ -93,7 +94,7 @@ export function useDictation({
}
}, 250);
} catch (error) {
await cancelActiveRecording();
await cancelActiveRecording(transcriptionSessionId);
if (!mountedRef.current) {
return;
}
Expand All @@ -103,7 +104,14 @@ export function useDictation({
});
console.error("[chat-dictation] failed to start recording", error);
}
}, [disabled, microphoneDevice, setPhase, stopElapsedTimer, t]);
}, [
disabled,
microphoneDevice,
setPhase,
stopElapsedTimer,
t,
transcriptionSessionId,
]);

const stop = useCallback(async () => {
if (phaseRef.current !== "recording") {
Expand All @@ -115,7 +123,9 @@ export function useDictation({
let recordedPath: string | null = null;

try {
const result = await dictationCommands.stopRecording();
const result = await dictationCommands.stopRecording(
transcriptionSessionId,
);
if (result.status === "error") {
throw new Error(result.error);
}
Expand Down Expand Up @@ -163,7 +173,14 @@ export function useDictation({
editorRef.current?.focus();
}
}
}, [editorRef, runBatch, setPhase, stopElapsedTimer, t]);
}, [
editorRef,
runBatch,
setPhase,
stopElapsedTimer,
t,
transcriptionSessionId,
]);
stopRef.current = stop;

useMountEffect(() => {
Expand All @@ -172,7 +189,7 @@ export function useDictation({
mountedRef.current = false;
stopElapsedTimer();
if (phaseRef.current === "starting" || phaseRef.current === "recording") {
void cancelActiveRecording();
void cancelActiveRecording(transcriptionSessionId);
}
};
});
Expand All @@ -185,9 +202,11 @@ export function useDictation({
};
}

async function cancelActiveRecording() {
async function cancelActiveRecording(transcriptionSessionId: string) {
try {
const result = await dictationCommands.cancelRecording();
const result = await dictationCommands.cancelRecording(
transcriptionSessionId,
);
if (result.status === "error") {
throw new Error(result.error);
}
Expand Down
Loading
Loading