Files
ChatApp/apps/desktop/src/lib/liveCaptions.ts
T
byGalax 825160ee46 feat(desktop): port v0.11.4-v0.15.2 from Tauri to Electron + Discord-parity audio (v0.16.0)
Chronological port of every Tauri release commit (v0.11.4 -> v0.15.2)
into the Electron rebuild, plus Discord-style audio handling that goes
beyond the Tauri original.

Highlights:
  - All 17 Tauri release commits ported (audio fixes, custom notification
    sound, Discord-style chat UX, profile banner, changelog page,
    Discord-parity call UX, screen-share echo + re-watch UX, audio-loop
    fix).
  - Native napi-rs audio-loopback addon with WASAPI process-loopback:
      * EXCLUDE_TARGET_PROCESS_TREE for full-screen shares -> peers
        never hear themselves echoed back through the capture.
      * INCLUDE_TARGET_PROCESS_TREE for window shares -> only the
        picked window's audio is captured, not the whole OS mixer
        (Discord parity).
      * HWND -> PID resolution via Win32 GetWindowThreadProcessId.
  - Discord-style screen-source picker (thumbnail grid, screens vs
    apps tabs, live-refreshing thumbnails).
  - Hash routing fix for packaged builds (file:// can't resolve
    BrowserRouter paths).
  - Tauri sources removed (apps/desktop/src-tauri).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 23:35:01 +02:00

120 lines
3.4 KiB
TypeScript

// Discord-style live captions. Uses the browser's SpeechRecognition API to
// transcribe the LOCAL user's mic, then broadcasts each interim/final result
// to peers via the LiveKit DataChannel. Receivers store and display them.
//
// Privacy note: speech recognition runs in the browser. On Chromium-based
// runtimes (incl. Tauri's WebView2 on Windows) this calls into the browser's
// own engine, which today reaches Google's cloud — same trade-off as Discord.
// We ship a hard off switch and require an explicit user toggle.
const STORAGE_KEY = 'chatapp.liveCaptions.v1';
export interface LiveCaptionsSettings {
enabled: boolean;
/** BCP-47 language tag, e.g. "de-DE" or "en-US". Auto-detect uses navigator.language. */
lang: string | null;
}
const DEFAULTS: LiveCaptionsSettings = {
enabled: false,
lang: null,
};
type Listener = (s: LiveCaptionsSettings) => void;
const listeners = new Set<Listener>();
let cached: LiveCaptionsSettings | null = null;
function read(): LiveCaptionsSettings {
if (cached) return cached;
try {
const raw = window.localStorage.getItem(STORAGE_KEY);
if (!raw) {
cached = DEFAULTS;
return cached;
}
const parsed = JSON.parse(raw) as Partial<LiveCaptionsSettings>;
cached = {
enabled: typeof parsed.enabled === 'boolean' ? parsed.enabled : DEFAULTS.enabled,
lang:
typeof parsed.lang === 'string' && parsed.lang.length > 0
? parsed.lang
: DEFAULTS.lang,
};
return cached;
} catch {
cached = DEFAULTS;
return cached;
}
}
function write(s: LiveCaptionsSettings): void {
cached = s;
try {
window.localStorage.setItem(STORAGE_KEY, JSON.stringify(s));
} catch {
/* quota / private mode */
}
for (const l of listeners) l(s);
}
export function getLiveCaptionsSettings(): LiveCaptionsSettings {
return read();
}
export function updateLiveCaptionsSettings(
patch: Partial<LiveCaptionsSettings>,
): LiveCaptionsSettings {
const next = { ...read(), ...patch };
write(next);
return next;
}
export function subscribeLiveCaptionsSettings(listener: Listener): () => void {
listeners.add(listener);
return () => listeners.delete(listener);
}
// Browser feature-detect. Chromium ships under both names; Firefox lacks it
// outright. Returns the constructor or null.
type SpeechRecognitionCtor = new () => SpeechRecognitionLike;
interface SpeechRecognitionLike extends EventTarget {
continuous: boolean;
interimResults: boolean;
lang: string;
start: () => void;
stop: () => void;
abort: () => void;
onresult: ((e: SpeechRecognitionEventLike) => void) | null;
onerror: ((e: SpeechRecognitionErrorLike) => void) | null;
onend: (() => void) | null;
}
interface SpeechRecognitionEventLike {
resultIndex: number;
results: ArrayLike<{
isFinal: boolean;
[index: number]: { transcript: string };
length: number;
}>;
}
interface SpeechRecognitionErrorLike {
error: string;
}
export function getSpeechRecognitionCtor(): SpeechRecognitionCtor | null {
const w = window as unknown as {
SpeechRecognition?: SpeechRecognitionCtor;
webkitSpeechRecognition?: SpeechRecognitionCtor;
};
return w.SpeechRecognition ?? w.webkitSpeechRecognition ?? null;
}
export function isLiveCaptionsSupported(): boolean {
return getSpeechRecognitionCtor() !== null;
}
export type {
SpeechRecognitionLike,
SpeechRecognitionEventLike,
SpeechRecognitionErrorLike,
};