feat(call): remove live-captions feature (privacy-inconsistent with E2E, unused)
This commit is contained in:
byGalax
@@ -1,119 +0,0 @@
|
||||
// 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,
|
||||
};
|
||||
@@ -1,142 +0,0 @@
|
||||
// Hook that runs SpeechRecognition on the local mic when live-captions are
|
||||
// enabled and a Room is connected. Each interim/final result is broadcast as
|
||||
// a `caption`-typed message via the LiveKit DataChannel so peers can render
|
||||
// it. Recognition stops cleanly when the call ends or the toggle flips off.
|
||||
|
||||
import type { Room } from 'livekit-client';
|
||||
import { useEffect, useRef } from 'react';
|
||||
|
||||
import {
|
||||
type LiveCaptionsSettings,
|
||||
getLiveCaptionsSettings,
|
||||
getSpeechRecognitionCtor,
|
||||
type SpeechRecognitionEventLike,
|
||||
type SpeechRecognitionLike,
|
||||
subscribeLiveCaptionsSettings,
|
||||
} from './liveCaptions';
|
||||
|
||||
interface Args {
|
||||
room: Room | null;
|
||||
/** True while we're connected and want captions to flow. */
|
||||
active: boolean;
|
||||
/** Callback fired locally for our own captions so the overlay can show
|
||||
* them without going through the SFU round-trip. */
|
||||
onLocalCaption: (text: string, final: boolean) => void;
|
||||
}
|
||||
|
||||
export function useLiveCaptions({ room, active, onLocalCaption }: Args): void {
|
||||
const recognitionRef = useRef<SpeechRecognitionLike | null>(null);
|
||||
const settingsRef = useRef<LiveCaptionsSettings>(getLiveCaptionsSettings());
|
||||
|
||||
useEffect(() => {
|
||||
return subscribeLiveCaptionsSettings((s) => {
|
||||
settingsRef.current = s;
|
||||
});
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
const Ctor = getSpeechRecognitionCtor();
|
||||
if (!Ctor) return; // unsupported runtime
|
||||
if (!active || !room) return;
|
||||
if (!getLiveCaptionsSettings().enabled) return;
|
||||
|
||||
const send = (text: string, final: boolean) => {
|
||||
onLocalCaption(text, final);
|
||||
try {
|
||||
const payload = new TextEncoder().encode(
|
||||
JSON.stringify({ type: 'caption', captionText: text, captionFinal: final }),
|
||||
);
|
||||
// Reliable channel — captions are infrequent enough to afford it,
|
||||
// and dropping interims looks worse than slight lag.
|
||||
void room.localParticipant.publishData(payload, { reliable: true });
|
||||
} catch {
|
||||
/* ignore — best-effort */
|
||||
}
|
||||
};
|
||||
|
||||
const start = () => {
|
||||
const r = new Ctor();
|
||||
r.continuous = true;
|
||||
r.interimResults = true;
|
||||
const lang = settingsRef.current.lang ?? navigator.language ?? 'de-DE';
|
||||
r.lang = lang;
|
||||
r.onresult = (e: SpeechRecognitionEventLike) => {
|
||||
// Pull whichever results arrived since last fire. Interim fires
|
||||
// many times per second; the final one is sticky and persists.
|
||||
for (let i = e.resultIndex; i < e.results.length; i++) {
|
||||
const result = e.results[i];
|
||||
if (!result || result.length === 0) continue;
|
||||
const alt = result[0];
|
||||
if (!alt) continue;
|
||||
const transcript = alt.transcript.trim();
|
||||
if (!transcript) continue;
|
||||
send(transcript, result.isFinal);
|
||||
}
|
||||
};
|
||||
r.onerror = () => {
|
||||
// Recoverable: stop + retry on next effect cycle. `not-allowed` and
|
||||
// `service-not-allowed` are permission-permanent — bail.
|
||||
try {
|
||||
r.stop();
|
||||
} catch {
|
||||
/* ignore */
|
||||
}
|
||||
};
|
||||
r.onend = () => {
|
||||
// SpeechRecognition tends to auto-stop after silence — if we still
|
||||
// want captions, restart it. Guard against tear-down race.
|
||||
if (recognitionRef.current === r && getLiveCaptionsSettings().enabled) {
|
||||
try {
|
||||
r.start();
|
||||
} catch {
|
||||
/* already running or browser refused */
|
||||
}
|
||||
}
|
||||
};
|
||||
try {
|
||||
r.start();
|
||||
recognitionRef.current = r;
|
||||
} catch {
|
||||
// Some browsers throw when start() is called too soon after a
|
||||
// previous abort — wait a tick and retry.
|
||||
window.setTimeout(() => {
|
||||
try {
|
||||
r.start();
|
||||
recognitionRef.current = r;
|
||||
} catch {
|
||||
/* give up */
|
||||
}
|
||||
}, 250);
|
||||
}
|
||||
};
|
||||
|
||||
start();
|
||||
|
||||
const unsub = subscribeLiveCaptionsSettings((s) => {
|
||||
const cur = recognitionRef.current;
|
||||
if (!s.enabled && cur) {
|
||||
recognitionRef.current = null;
|
||||
try {
|
||||
cur.abort();
|
||||
} catch {
|
||||
/* ignore */
|
||||
}
|
||||
} else if (s.enabled && !cur) {
|
||||
start();
|
||||
}
|
||||
});
|
||||
|
||||
return () => {
|
||||
unsub();
|
||||
const cur = recognitionRef.current;
|
||||
recognitionRef.current = null;
|
||||
if (cur) {
|
||||
try {
|
||||
cur.abort();
|
||||
} catch {
|
||||
/* ignore */
|
||||
}
|
||||
}
|
||||
};
|
||||
}, [active, room, onLocalCaption]);
|
||||
}
|
||||
Reference in New Issue
Block a user