common frontend for web/ and chrome extension

This commit is contained in:
Quentin Fuxa
2025-09-25 23:14:25 +02:00
parent d24c110d55
commit 9fc6654a4a
17 changed files with 212 additions and 1335 deletions

View File

@@ -54,7 +54,15 @@ pip install whisperlivekit
> - See [tokenizer.py](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py) for the list of all available languages.
> - For HTTPS requirements, see the **Parameters** section for SSL configuration options.
#### Use it to capture audio from web pages.
Go to `chrome-extension` for instructions.
<p align="center">
<img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/chrome-extension/demo-extension.png" alt="WhisperLiveKit Demo" width="600">
</p>
#### Optional Dependencies

View File

@@ -1,11 +1,13 @@
## WhisperLiveKit Chrome Extension v0.1.0
Capture the audio of your current tab, transcribe or translate it using WhisperliveKit. **Still unstable**
## WhisperLiveKit Chrome Extension v0.1.1
Capture the audio of your current tab, transcribe diarize and translate it using WhisperliveKit, in Chrome and other Chromium-based browsers.
> Currently, only the tab audio is captured; your microphone audio is not recorded.
<img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/chrome-extension/demo-extension.png" alt="WhisperLiveKit Demo" width="730">
## Running this extension
1. Clone this repository.
2. Load this directory in Chrome as an unpacked extension.
1. Run `python sync_extension.py` to copy frontend files to the `chrome-extension` directory.
2. Load the `chrome-extension` directory in Chrome as an unpacked extension.
## Devs:

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.2 MiB

After

Width:  |  Height:  |  Size: 2.6 MiB

View File

@@ -1,669 +0,0 @@
/* Theme, WebSocket, recording, rendering logic extracted from inline script and adapted for segmented theme control and WS caption */
let isRecording = false;
let websocket = null;
let recorder = null;
let chunkDuration = 100;
let websocketUrl = "ws://localhost:8000/asr";
let userClosing = false;
let wakeLock = null;
let startTime = null;
let timerInterval = null;
let audioContext = null;
let analyser = null;
let microphone = null;
let waveCanvas = document.getElementById("waveCanvas");
let waveCtx = waveCanvas.getContext("2d");
let animationFrame = null;
let waitingForStop = false;
let lastReceivedData = null;
let lastSignature = null;
let availableMicrophones = [];
let selectedMicrophoneId = null;
waveCanvas.width = 60 * (window.devicePixelRatio || 1);
waveCanvas.height = 30 * (window.devicePixelRatio || 1);
waveCtx.scale(window.devicePixelRatio || 1, window.devicePixelRatio || 1);
const statusText = document.getElementById("status");
const recordButton = document.getElementById("recordButton");
const chunkSelector = document.getElementById("chunkSelector");
const websocketInput = document.getElementById("websocketInput");
const websocketDefaultSpan = document.getElementById("wsDefaultUrl");
const linesTranscriptDiv = document.getElementById("linesTranscript");
const timerElement = document.querySelector(".timer");
const themeRadios = document.querySelectorAll('input[name="theme"]');
const microphoneSelect = document.getElementById("microphoneSelect");
const settingsToggle = document.getElementById("settingsToggle");
const settingsDiv = document.querySelector(".settings");
chrome.runtime.onInstalled.addListener((details) => {
if (details.reason.search(/install/g) === -1) {
return
}
chrome.tabs.create({
url: chrome.runtime.getURL("welcome.html"),
active: true
})
})
function getWaveStroke() {
const styles = getComputedStyle(document.documentElement);
const v = styles.getPropertyValue("--wave-stroke").trim();
return v || "#000";
}
let waveStroke = getWaveStroke();
function updateWaveStroke() {
waveStroke = getWaveStroke();
}
function applyTheme(pref) {
if (pref === "light") {
document.documentElement.setAttribute("data-theme", "light");
} else if (pref === "dark") {
document.documentElement.setAttribute("data-theme", "dark");
} else {
document.documentElement.removeAttribute("data-theme");
}
updateWaveStroke();
}
// Persisted theme preference
const savedThemePref = localStorage.getItem("themePreference") || "system";
applyTheme(savedThemePref);
if (themeRadios.length) {
themeRadios.forEach((r) => {
r.checked = r.value === savedThemePref;
r.addEventListener("change", () => {
if (r.checked) {
localStorage.setItem("themePreference", r.value);
applyTheme(r.value);
}
});
});
}
// React to OS theme changes when in "system" mode
const darkMq = window.matchMedia && window.matchMedia("(prefers-color-scheme: dark)");
const handleOsThemeChange = () => {
const pref = localStorage.getItem("themePreference") || "system";
if (pref === "system") updateWaveStroke();
};
if (darkMq && darkMq.addEventListener) {
darkMq.addEventListener("change", handleOsThemeChange);
} else if (darkMq && darkMq.addListener) {
// deprecated, but included for Safari compatibility
darkMq.addListener(handleOsThemeChange);
}
async function enumerateMicrophones() {
try {
const micPermission = await navigator.permissions.query({
name: "microphone",
});
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
stream.getTracks().forEach(track => track.stop());
const devices = await navigator.mediaDevices.enumerateDevices();
availableMicrophones = devices.filter(device => device.kind === 'audioinput');
populateMicrophoneSelect();
console.log(`Found ${availableMicrophones.length} microphone(s)`);
} catch (error) {
console.error('Error enumerating microphones:', error);
statusText.textContent = "Error accessing microphones. Please grant permission.";
}
}
function populateMicrophoneSelect() {
if (!microphoneSelect) return;
microphoneSelect.innerHTML = '<option value="">Default Microphone</option>';
availableMicrophones.forEach((device, index) => {
const option = document.createElement('option');
option.value = device.deviceId;
option.textContent = device.label || `Microphone ${index + 1}`;
microphoneSelect.appendChild(option);
});
const savedMicId = localStorage.getItem('selectedMicrophone');
if (savedMicId && availableMicrophones.some(mic => mic.deviceId === savedMicId)) {
microphoneSelect.value = savedMicId;
selectedMicrophoneId = savedMicId;
}
}
function handleMicrophoneChange() {
selectedMicrophoneId = microphoneSelect.value || null;
localStorage.setItem('selectedMicrophone', selectedMicrophoneId || '');
const selectedDevice = availableMicrophones.find(mic => mic.deviceId === selectedMicrophoneId);
const deviceName = selectedDevice ? selectedDevice.label : 'Default Microphone';
console.log(`Selected microphone: ${deviceName}`);
statusText.textContent = `Microphone changed to: ${deviceName}`;
if (isRecording) {
statusText.textContent = "Switching microphone... Please wait.";
stopRecording().then(() => {
setTimeout(() => {
toggleRecording();
}, 1000);
});
}
}
// Helpers
function fmt1(x) {
const n = Number(x);
return Number.isFinite(n) ? n.toFixed(1) : x;
}
// Default WebSocket URL computation
const host = window.location.hostname || "localhost";
const port = window.location.port;
const protocol = window.location.protocol === "https:" ? "wss" : "ws";
const defaultWebSocketUrl = websocketUrl;
// Populate default caption and input
if (websocketDefaultSpan) websocketDefaultSpan.textContent = defaultWebSocketUrl;
websocketInput.value = defaultWebSocketUrl;
websocketUrl = defaultWebSocketUrl;
// Optional chunk selector (guard for presence)
if (chunkSelector) {
chunkSelector.addEventListener("change", () => {
chunkDuration = parseInt(chunkSelector.value);
});
}
// WebSocket input change handling
websocketInput.addEventListener("change", () => {
const urlValue = websocketInput.value.trim();
if (!urlValue.startsWith("ws://") && !urlValue.startsWith("wss://")) {
statusText.textContent = "Invalid WebSocket URL (must start with ws:// or wss://)";
return;
}
websocketUrl = urlValue;
statusText.textContent = "WebSocket URL updated. Ready to connect.";
});
function setupWebSocket() {
return new Promise((resolve, reject) => {
try {
websocket = new WebSocket(websocketUrl);
} catch (error) {
statusText.textContent = "Invalid WebSocket URL. Please check and try again.";
reject(error);
return;
}
websocket.onopen = () => {
statusText.textContent = "Connected to server.";
resolve();
};
websocket.onclose = () => {
if (userClosing) {
if (waitingForStop) {
statusText.textContent = "Processing finalized or connection closed.";
if (lastReceivedData) {
renderLinesWithBuffer(
lastReceivedData.lines || [],
lastReceivedData.buffer_diarization || "",
lastReceivedData.buffer_transcription || "",
0,
0,
true
);
}
}
} else {
statusText.textContent = "Disconnected from the WebSocket server. (Check logs if model is loading.)";
if (isRecording) {
stopRecording();
}
}
isRecording = false;
waitingForStop = false;
userClosing = false;
lastReceivedData = null;
websocket = null;
updateUI();
};
websocket.onerror = () => {
statusText.textContent = "Error connecting to WebSocket.";
reject(new Error("Error connecting to WebSocket"));
};
websocket.onmessage = (event) => {
const data = JSON.parse(event.data);
if (data.type === "ready_to_stop") {
console.log("Ready to stop received, finalizing display and closing WebSocket.");
waitingForStop = false;
if (lastReceivedData) {
renderLinesWithBuffer(
lastReceivedData.lines || [],
lastReceivedData.buffer_diarization || "",
lastReceivedData.buffer_transcription || "",
0,
0,
true
);
}
statusText.textContent = "Finished processing audio! Ready to record again.";
recordButton.disabled = false;
if (websocket) {
websocket.close();
}
return;
}
lastReceivedData = data;
const {
lines = [],
buffer_transcription = "",
buffer_diarization = "",
remaining_time_transcription = 0,
remaining_time_diarization = 0,
status = "active_transcription",
} = data;
renderLinesWithBuffer(
lines,
buffer_diarization,
buffer_transcription,
remaining_time_diarization,
remaining_time_transcription,
false,
status
);
};
});
}
function renderLinesWithBuffer(
lines,
buffer_diarization,
buffer_transcription,
remaining_time_diarization,
remaining_time_transcription,
isFinalizing = false,
current_status = "active_transcription"
) {
if (current_status === "no_audio_detected") {
linesTranscriptDiv.innerHTML =
"<p style='text-align: center; color: var(--muted); margin-top: 20px;'><em>No audio detected...</em></p>";
return;
}
const showLoading = !isFinalizing && (lines || []).some((it) => it.speaker == 0);
const showTransLag = !isFinalizing && remaining_time_transcription > 0;
const showDiaLag = !isFinalizing && !!buffer_diarization && remaining_time_diarization > 0;
const signature = JSON.stringify({
lines: (lines || []).map((it) => ({ speaker: it.speaker, text: it.text, start: it.start, end: it.end })),
buffer_transcription: buffer_transcription || "",
buffer_diarization: buffer_diarization || "",
status: current_status,
showLoading,
showTransLag,
showDiaLag,
isFinalizing: !!isFinalizing,
});
if (lastSignature === signature) {
const t = document.querySelector(".lag-transcription-value");
if (t) t.textContent = fmt1(remaining_time_transcription);
const d = document.querySelector(".lag-diarization-value");
if (d) d.textContent = fmt1(remaining_time_diarization);
const ld = document.querySelector(".loading-diarization-value");
if (ld) ld.textContent = fmt1(remaining_time_diarization);
return;
}
lastSignature = signature;
const linesHtml = (lines || [])
.map((item, idx) => {
let timeInfo = "";
if (item.start !== undefined && item.end !== undefined) {
timeInfo = ` ${item.start} - ${item.end}`;
}
let speakerLabel = "";
if (item.speaker === -2) {
speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
} else if (item.speaker == 0 && !isFinalizing) {
speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'><span class="loading-diarization-value">${fmt1(
remaining_time_diarization
)}</span> second(s) of audio are undergoing diarization</span></span>`;
} else if (item.speaker !== 0) {
speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
}
let currentLineText = item.text || "";
if (idx === lines.length - 1) {
if (!isFinalizing && item.speaker !== -2) {
if (remaining_time_transcription > 0) {
speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Lag <span id='timeInfo'><span class="lag-transcription-value">${fmt1(
remaining_time_transcription
)}</span>s</span></span>`;
}
if (buffer_diarization && remaining_time_diarization > 0) {
speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Lag<span id='timeInfo'><span class="lag-diarization-value">${fmt1(
remaining_time_diarization
)}</span>s</span></span>`;
}
}
if (buffer_diarization) {
if (isFinalizing) {
currentLineText +=
(currentLineText.length > 0 && buffer_diarization.trim().length > 0 ? " " : "") + buffer_diarization.trim();
} else {
currentLineText += `<span class="buffer_diarization">${buffer_diarization}</span>`;
}
}
if (buffer_transcription) {
if (isFinalizing) {
currentLineText +=
(currentLineText.length > 0 && buffer_transcription.trim().length > 0 ? " " : "") +
buffer_transcription.trim();
} else {
currentLineText += `<span class="buffer_transcription">${buffer_transcription}</span>`;
}
}
}
return currentLineText.trim().length > 0 || speakerLabel.length > 0
? `<p>${speakerLabel}<br/><div class='textcontent'>${currentLineText}</div></p>`
: `<p>${speakerLabel}<br/></p>`;
})
.join("");
linesTranscriptDiv.innerHTML = linesHtml;
window.scrollTo({ top: document.body.scrollHeight, behavior: "smooth" });
}
function updateTimer() {
if (!startTime) return;
const elapsed = Math.floor((Date.now() - startTime) / 1000);
const minutes = Math.floor(elapsed / 60).toString().padStart(2, "0");
const seconds = (elapsed % 60).toString().padStart(2, "0");
timerElement.textContent = `${minutes}:${seconds}`;
}
function drawWaveform() {
if (!analyser) return;
const bufferLength = analyser.frequencyBinCount;
const dataArray = new Uint8Array(bufferLength);
analyser.getByteTimeDomainData(dataArray);
waveCtx.clearRect(
0,
0,
waveCanvas.width / (window.devicePixelRatio || 1),
waveCanvas.height / (window.devicePixelRatio || 1)
);
waveCtx.lineWidth = 1;
waveCtx.strokeStyle = waveStroke;
waveCtx.beginPath();
const sliceWidth = (waveCanvas.width / (window.devicePixelRatio || 1)) / bufferLength;
let x = 0;
for (let i = 0; i < bufferLength; i++) {
const v = dataArray[i] / 128.0;
const y = (v * (waveCanvas.height / (window.devicePixelRatio || 1))) / 2;
if (i === 0) {
waveCtx.moveTo(x, y);
} else {
waveCtx.lineTo(x, y);
}
x += sliceWidth;
}
waveCtx.lineTo(
waveCanvas.width / (window.devicePixelRatio || 1),
(waveCanvas.height / (window.devicePixelRatio || 1)) / 2
);
waveCtx.stroke();
animationFrame = requestAnimationFrame(drawWaveform);
}
async function startRecording() {
try {
try {
wakeLock = await navigator.wakeLock.request("screen");
} catch (err) {
console.log("Error acquiring wake lock.");
}
let stream;
try {
// Try tab capture first
stream = await new Promise((resolve, reject) => {
chrome.tabCapture.capture({audio: true}, (s) => {
if (s) {
resolve(s);
} else {
reject(new Error('Tab capture failed or not available'));
}
});
});
statusText.textContent = "Using tab audio capture.";
} catch (tabError) {
console.log('Tab capture not available, falling back to microphone', tabError);
// Fallback to microphone
const audioConstraints = selectedMicrophoneId
? { audio: { deviceId: { exact: selectedMicrophoneId } } }
: { audio: true };
stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
statusText.textContent = "Using microphone audio.";
}
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
analyser.fftSize = 256;
microphone = audioContext.createMediaStreamSource(stream);
microphone.connect(analyser);
recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
recorder.ondataavailable = (e) => {
if (websocket && websocket.readyState === WebSocket.OPEN) {
websocket.send(e.data);
}
};
recorder.start(chunkDuration);
startTime = Date.now();
timerInterval = setInterval(updateTimer, 1000);
drawWaveform();
isRecording = true;
updateUI();
} catch (err) {
if (window.location.hostname === "0.0.0.0") {
statusText.textContent =
"Error accessing audio input. Browsers may block audio access on 0.0.0.0. Try using localhost:8000 instead.";
} else {
statusText.textContent = "Error accessing audio input. Please check permissions.";
}
console.error(err);
}
}
async function stopRecording() {
if (wakeLock) {
try {
await wakeLock.release();
} catch (e) {
// ignore
}
wakeLock = null;
}
userClosing = true;
waitingForStop = true;
if (websocket && websocket.readyState === WebSocket.OPEN) {
const emptyBlob = new Blob([], { type: "audio/webm" });
websocket.send(emptyBlob);
statusText.textContent = "Recording stopped. Processing final audio...";
}
if (recorder) {
recorder.stop();
recorder = null;
}
if (microphone) {
microphone.disconnect();
microphone = null;
}
if (analyser) {
analyser = null;
}
if (audioContext && audioContext.state !== "closed") {
try {
await audioContext.close();
} catch (e) {
console.warn("Could not close audio context:", e);
}
audioContext = null;
}
if (animationFrame) {
cancelAnimationFrame(animationFrame);
animationFrame = null;
}
if (timerInterval) {
clearInterval(timerInterval);
timerInterval = null;
}
timerElement.textContent = "00:00";
startTime = null;
isRecording = false;
updateUI();
}
async function toggleRecording() {
if (!isRecording) {
if (waitingForStop) {
console.log("Waiting for stop, early return");
return;
}
console.log("Connecting to WebSocket");
try {
if (websocket && websocket.readyState === WebSocket.OPEN) {
await startRecording();
} else {
await setupWebSocket();
await startRecording();
}
} catch (err) {
statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
console.error(err);
}
} else {
console.log("Stopping recording");
stopRecording();
}
}
function updateUI() {
recordButton.classList.toggle("recording", isRecording);
recordButton.disabled = waitingForStop;
if (waitingForStop) {
if (statusText.textContent !== "Recording stopped. Processing final audio...") {
statusText.textContent = "Please wait for processing to complete...";
}
} else if (isRecording) {
statusText.textContent = "Recording...";
} else {
if (
statusText.textContent !== "Finished processing audio! Ready to record again." &&
statusText.textContent !== "Processing finalized or connection closed."
) {
statusText.textContent = "Click to start transcription";
}
}
if (!waitingForStop) {
recordButton.disabled = false;
}
}
recordButton.addEventListener("click", toggleRecording);
if (microphoneSelect) {
microphoneSelect.addEventListener("change", handleMicrophoneChange);
}
// Settings toggle functionality
settingsToggle.addEventListener("click", () => {
settingsDiv.classList.toggle("visible");
settingsToggle.classList.toggle("active");
});
document.addEventListener('DOMContentLoaded', async () => {
try {
await enumerateMicrophones();
} catch (error) {
console.log("Could not enumerate microphones on load:", error);
}
});
navigator.mediaDevices.addEventListener('devicechange', async () => {
console.log('Device change detected, re-enumerating microphones');
try {
await enumerateMicrophones();
} catch (error) {
console.log("Error re-enumerating microphones:", error);
}
});
async function run() {
const micPermission = await navigator.permissions.query({
name: "microphone",
});
document.getElementById(
"audioPermission"
).innerText = `MICROPHONE: ${micPermission.state}`;
if (micPermission.state !== "granted") {
chrome.tabs.create({ url: "welcome.html" });
}
const intervalId = setInterval(async () => {
const micPermission = await navigator.permissions.query({
name: "microphone",
});
if (micPermission.state === "granted") {
document.getElementById(
"audioPermission"
).innerText = `MICROPHONE: ${micPermission.state}`;
clearInterval(intervalId);
}
}, 100);
}
void run();

View File

@@ -3,9 +3,6 @@
"name": "WhisperLiveKit Tab Capture",
"version": "1.0",
"description": "Capture and transcribe audio from browser tabs using WhisperLiveKit.",
"background": {
"service_worker": "background.js"
},
"icons": {
"16": "icons/icon16.png",
"32": "icons/icon32.png",
@@ -14,7 +11,7 @@
},
"action": {
"default_title": "WhisperLiveKit Tab Capture",
"default_popup": "popup.html"
"default_popup": "live_transcription.html"
},
"permissions": [
"scripting",
@@ -22,16 +19,5 @@
"offscreen",
"activeTab",
"storage"
],
"web_accessible_resources": [
{
"resources": [
"requestPermissions.html",
"requestPermissions.js"
],
"matches": [
"<all_urls>"
]
}
]
}

View File

@@ -1,78 +0,0 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>WhisperLiveKit</title>
<link rel="stylesheet" href="/web/live_transcription.css" />
</head>
<body>
<div class="settings-container">
<button id="recordButton">
<div class="shape-container">
<div class="shape"></div>
</div>
<div class="recording-info">
<div class="wave-container">
<canvas id="waveCanvas"></canvas>
</div>
<div class="timer">00:00</div>
</div>
</button>
<button id="settingsToggle" class="settings-toggle" title="Show/hide settings">
<img src="/web/src/settings.svg" alt="Settings" />
</button>
<div class="settings">
<div class="field">
<label for="websocketInput">Websocket URL</label>
<input id="websocketInput" type="text" placeholder="ws://host:port/asr" />
</div>
<div class="field">
<label id="microphoneSelectLabel" for="microphoneSelect">Select Microphone</label>
<select id="microphoneSelect">
<option value="">Default Microphone</option>
</select>
<div id="audioPermission"></div>
</div>
<div class="theme-selector-container">
<div class="segmented" role="radiogroup" aria-label="Theme selector">
<input type="radio" id="theme-system" name="theme" value="system" />
<label for="theme-system" title="System">
<img src="/web/src/system_mode.svg" alt="" />
<!-- <span>System</span> -->
</label>
<input type="radio" id="theme-light" name="theme" value="light" />
<label for="theme-light" title="Light">
<img src="/web/src/light_mode.svg" alt="" />
<!-- <span>Light</span> -->
</label>
<input type="radio" id="theme-dark" name="theme" value="dark" />
<label for="theme-dark" title="Dark">
<img src="/web/src/dark_mode.svg" alt="" />
<!-- <span>Dark</span> -->
</label>
</div>
</div>
</div>
</div>
<p id="status"></p>
<div id="linesTranscript"></div>
<script src="live_transcription.js"></script>
</body>
</html>

View File

@@ -1,539 +0,0 @@
:root {
--bg: #ffffff;
--text: #111111;
--muted: #666666;
--border: #e5e5e5;
--chip-bg: rgba(0, 0, 0, 0.04);
--chip-text: #000000;
--spinner-border: #8d8d8d5c;
--spinner-top: #b0b0b0;
--silence-bg: #f3f3f3;
--loading-bg: rgba(255, 77, 77, 0.06);
--button-bg: #ffffff;
--button-border: #e9e9e9;
--wave-stroke: #000000;
--label-dia-text: #868686;
--label-trans-text: #111111;
}
@media (prefers-color-scheme: dark) {
:root:not([data-theme="light"]) {
--bg: #0b0b0b;
--text: #e6e6e6;
--muted: #9aa0a6;
--border: #333333;
--chip-bg: rgba(255, 255, 255, 0.08);
--chip-text: #e6e6e6;
--spinner-border: #555555;
--spinner-top: #dddddd;
--silence-bg: #1a1a1a;
--loading-bg: rgba(255, 77, 77, 0.12);
--button-bg: #111111;
--button-border: #333333;
--wave-stroke: #e6e6e6;
--label-dia-text: #b3b3b3;
--label-trans-text: #ffffff;
}
}
:root[data-theme="dark"] {
--bg: #0b0b0b;
--text: #e6e6e6;
--muted: #9aa0a6;
--border: #333333;
--chip-bg: rgba(255, 255, 255, 0.08);
--chip-text: #e6e6e6;
--spinner-border: #555555;
--spinner-top: #dddddd;
--silence-bg: #1a1a1a;
--loading-bg: rgba(255, 77, 77, 0.12);
--button-bg: #111111;
--button-border: #333333;
--wave-stroke: #e6e6e6;
--label-dia-text: #b3b3b3;
--label-trans-text: #ffffff;
}
:root[data-theme="light"] {
--bg: #ffffff;
--text: #111111;
--muted: #666666;
--border: #e5e5e5;
--chip-bg: rgba(0, 0, 0, 0.04);
--chip-text: #000000;
--spinner-border: #8d8d8d5c;
--spinner-top: #b0b0b0;
--silence-bg: #f3f3f3;
--loading-bg: rgba(255, 77, 77, 0.06);
--button-bg: #ffffff;
--button-border: #e9e9e9;
--wave-stroke: #000000;
--label-dia-text: #868686;
--label-trans-text: #111111;
}
body {
font-family: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
margin: 20px;
text-align: center;
background-color: var(--bg);
color: var(--text);
}
.settings-toggle {
margin-top: 4px;
width: 40px;
height: 40px;
border: none;
border-radius: 50%;
background-color: var(--button-bg);
cursor: pointer;
transition: all 0.3s ease;
/* border: 1px solid var(--button-border); */
display: flex;
align-items: center;
justify-content: center;
position: relative;
}
.settings-toggle:hover {
background-color: var(--chip-bg);
}
.settings-toggle img {
width: 24px;
height: 24px;
opacity: 0.7;
transition: opacity 0.2s ease, transform 0.3s ease;
}
.settings-toggle:hover img {
opacity: 1;
}
.settings-toggle.active img {
transform: rotate(80deg);
}
/* Record button */
#recordButton {
width: 50px;
height: 50px;
border: none;
border-radius: 50%;
background-color: var(--button-bg);
cursor: pointer;
transition: all 0.3s ease;
border: 1px solid var(--button-border);
display: flex;
align-items: center;
justify-content: center;
position: relative;
}
#recordButton.recording {
width: 180px;
border-radius: 40px;
justify-content: flex-start;
padding-left: 20px;
}
#recordButton:active {
transform: scale(0.95);
}
.shape-container {
width: 25px;
height: 25px;
display: flex;
align-items: center;
justify-content: center;
flex-shrink: 0;
}
.shape {
width: 25px;
height: 25px;
background-color: rgb(209, 61, 53);
border-radius: 50%;
transition: all 0.3s ease;
}
#recordButton:disabled .shape {
background-color: #6e6d6d;
}
#recordButton.recording .shape {
border-radius: 5px;
width: 25px;
height: 25px;
}
/* Recording elements */
.recording-info {
display: none;
align-items: center;
margin-left: 15px;
flex-grow: 1;
}
#recordButton.recording .recording-info {
display: flex;
}
.wave-container {
width: 60px;
height: 30px;
position: relative;
display: flex;
align-items: center;
justify-content: center;
}
#waveCanvas {
width: 100%;
height: 100%;
}
.timer {
font-size: 14px;
font-weight: 500;
color: var(--text);
margin-left: 10px;
}
#status {
margin-top: 20px;
font-size: 16px;
color: var(--text);
}
/* Settings */
.settings-container {
display: flex;
justify-content: center;
align-items: flex-start;
gap: 15px;
margin-top: 20px;
flex-wrap: wrap;
}
.settings {
display: none;
flex-wrap: wrap;
align-items: flex-start;
gap: 12px;
transition: opacity 0.3s ease;
}
.settings.visible {
display: flex;
}
.field {
display: flex;
flex-direction: column;
align-items: flex-start;
gap: 3px;
}
#chunkSelector,
#websocketInput,
#themeSelector,
#microphoneSelect {
font-size: 16px;
padding: 5px 8px;
border-radius: 8px;
border: 1px solid var(--border);
background-color: var(--button-bg);
color: var(--text);
max-height: 30px;
}
#microphoneSelect {
width: 100%;
max-width: 190px;
min-width: 120px;
}
#chunkSelector:focus,
#websocketInput:focus,
#themeSelector:focus,
#microphoneSelect:focus {
outline: none;
border-color: #007bff;
box-shadow: 0 0 0 3px rgba(0, 123, 255, 0.15);
}
label {
font-size: 13px;
color: var(--muted);
}
.ws-default {
font-size: 12px;
color: var(--muted);
}
/* Segmented pill control for Theme */
.segmented {
display: inline-flex;
align-items: stretch;
border: 1px solid var(--button-border);
background-color: var(--button-bg);
border-radius: 999px;
overflow: hidden;
}
.segmented input[type="radio"] {
position: absolute;
opacity: 0;
pointer-events: none;
}
.theme-selector-container {
display: flex;
align-items: center;
margin-top: 17px;
}
.segmented label {
display: inline-flex;
align-items: center;
gap: 6px;
padding: 6px 12px;
font-size: 14px;
color: var(--muted);
cursor: pointer;
user-select: none;
transition: background-color 0.2s ease, color 0.2s ease;
}
.segmented label span {
display: none;
}
.segmented label:hover span {
display: inline;
}
.segmented label:hover {
background-color: var(--chip-bg);
}
.segmented img {
width: 16px;
height: 16px;
}
.segmented input[type="radio"]:checked + label {
background-color: var(--chip-bg);
color: var(--text);
}
.segmented input[type="radio"]:focus-visible + label,
.segmented input[type="radio"]:focus + label {
outline: 2px solid #007bff;
outline-offset: 2px;
border-radius: 999px;
}
/* Transcript area */
#linesTranscript {
margin: 20px auto;
max-width: 700px;
text-align: left;
font-size: 16px;
}
#linesTranscript p {
margin: 0px 0;
}
#linesTranscript strong {
color: var(--text);
}
#speaker {
border: 1px solid var(--border);
border-radius: 100px;
padding: 2px 10px;
font-size: 14px;
margin-bottom: 0px;
}
.label_diarization {
background-color: var(--chip-bg);
border-radius: 8px 8px 8px 8px;
padding: 2px 10px;
margin-left: 10px;
display: inline-block;
white-space: nowrap;
font-size: 14px;
margin-bottom: 0px;
color: var(--label-dia-text);
}
.label_transcription {
background-color: var(--chip-bg);
border-radius: 8px 8px 8px 8px;
padding: 2px 10px;
display: inline-block;
white-space: nowrap;
margin-left: 10px;
font-size: 14px;
margin-bottom: 0px;
color: var(--label-trans-text);
}
#timeInfo {
color: var(--muted);
margin-left: 10px;
}
.textcontent {
font-size: 16px;
padding-left: 10px;
margin-bottom: 10px;
margin-top: 1px;
padding-top: 5px;
border-radius: 0px 0px 0px 10px;
}
.buffer_diarization {
color: var(--label-dia-text);
margin-left: 4px;
}
.buffer_transcription {
color: #7474748c;
margin-left: 4px;
}
.spinner {
display: inline-block;
width: 8px;
height: 8px;
border: 2px solid var(--spinner-border);
border-top: 2px solid var(--spinner-top);
border-radius: 50%;
animation: spin 0.7s linear infinite;
vertical-align: middle;
margin-bottom: 2px;
margin-right: 5px;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
.silence {
color: var(--muted);
background-color: var(--silence-bg);
font-size: 13px;
border-radius: 30px;
padding: 2px 10px;
}
.loading {
color: var(--muted);
background-color: var(--loading-bg);
border-radius: 8px 8px 8px 0px;
padding: 2px 10px;
font-size: 14px;
margin-bottom: 0px;
}
/* for smaller screens */
/* @media (max-width: 450px) {
.settings-container {
flex-direction: column;
gap: 10px;
align-items: center;
}
.settings {
justify-content: center;
gap: 8px;
width: 100%;
}
.field {
align-items: center;
width: 100%;
}
#websocketInput,
#microphoneSelect {
min-width: 200px;
max-width: 100%;
}
.theme-selector-container {
margin-top: 10px;
}
} */
/* @media (max-width: 768px) and (min-width: 451px) {
.settings-container {
gap: 10px;
}
.settings {
gap: 8px;
}
#websocketInput,
#microphoneSelect {
min-width: 150px;
max-width: 300px;
}
} */
/* @media (max-width: 480px) {
body {
margin: 10px;
}
.settings-toggle {
width: 35px;
height: 35px;
}
.settings-toggle img {
width: 20px;
height: 20px;
}
.settings {
flex-direction: column;
align-items: center;
gap: 6px;
}
#websocketInput,
#microphoneSelect {
max-width: 400px;
}
.segmented label {
padding: 4px 8px;
font-size: 12px;
}
.segmented img {
width: 14px;
height: 14px;
}
} */
html
{
width: 400px; /* max: 800px */
height: 600px; /* max: 600px */
border-radius: 10px;
}

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M480-120q-151 0-255.5-104.5T120-480q0-138 90-239.5T440-838q13-2 23 3.5t16 14.5q6 9 6.5 21t-7.5 23q-17 26-25.5 55t-8.5 61q0 90 63 153t153 63q31 0 61.5-9t54.5-25q11-7 22.5-6.5T819-479q10 5 15.5 15t3.5 24q-14 138-117.5 229T480-120Zm0-80q88 0 158-48.5T740-375q-20 5-40 8t-40 3q-123 0-209.5-86.5T364-660q0-20 3-40t8-40q-78 32-126.5 102T200-480q0 116 82 198t198 82Zm-10-270Z"/></svg>

Before

Width:  |  Height:  |  Size: 493 B

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Zm0 80q-83 0-141.5-58.5T280-480q0-83 58.5-141.5T480-680q83 0 141.5 58.5T680-480q0 83-58.5 141.5T480-280ZM80-440q-17 0-28.5-11.5T40-480q0-17 11.5-28.5T80-520h80q17 0 28.5 11.5T200-480q0 17-11.5 28.5T160-440H80Zm720 0q-17 0-28.5-11.5T760-480q0-17 11.5-28.5T800-520h80q17 0 28.5 11.5T920-480q0 17-11.5 28.5T880-440h-80ZM480-760q-17 0-28.5-11.5T440-800v-80q0-17 11.5-28.5T480-920q17 0 28.5 11.5T520-880v80q0 17-11.5 28.5T480-760Zm0 720q-17 0-28.5-11.5T440-80v-80q0-17 11.5-28.5T480-200q17 0 28.5 11.5T520-160v80q0 17-11.5 28.5T480-40ZM226-678l-43-42q-12-11-11.5-28t11.5-29q12-12 29-12t28 12l42 43q11 12 11 28t-11 28q-11 12-27.5 11.5T226-678Zm494 495-42-43q-11-12-11-28.5t11-27.5q11-12 27.5-11.5T734-282l43 42q12 11 11.5 28T777-183q-12 12-29 12t-28-12Zm-42-495q-12-11-11.5-27.5T678-734l42-43q11-12 28-11.5t29 11.5q12 12 12 29t-12 28l-43 42q-12 11-28 11t-28-11ZM183-183q-12-12-12-29t12-28l43-42q12-11 28.5-11t27.5 11q12 11 11.5 27.5T282-226l-42 43q-11 12-28 11.5T183-183Zm297-297Z"/></svg>

Before

Width:  |  Height:  |  Size: 1.2 KiB

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M433-80q-27 0-46.5-18T363-142l-9-66q-13-5-24.5-12T307-235l-62 26q-25 11-50 2t-39-32l-47-82q-14-23-8-49t27-43l53-40q-1-7-1-13.5v-27q0-6.5 1-13.5l-53-40q-21-17-27-43t8-49l47-82q14-23 39-32t50 2l62 26q11-8 23-15t24-12l9-66q4-26 23.5-44t46.5-18h94q27 0 46.5 18t23.5 44l9 66q13 5 24.5 12t22.5 15l62-26q25-11 50-2t39 32l47 82q14 23 8 49t-27 43l-53 40q1 7 1 13.5v27q0 6.5-2 13.5l53 40q21 17 27 43t-8 49l-48 82q-14 23-39 32t-50-2l-60-26q-11 8-23 15t-24 12l-9 66q-4 26-23.5 44T527-80h-94Zm7-80h79l14-106q31-8 57.5-23.5T639-327l99 41 39-68-86-65q5-14 7-29.5t2-31.5q0-16-2-31.5t-7-29.5l86-65-39-68-99 42q-22-23-48.5-38.5T533-694l-13-106h-79l-14 106q-31 8-57.5 23.5T321-633l-99-41-39 68 86 64q-5 15-7 30t-2 32q0 16 2 31t7 30l-86 65 39 68 99-42q22 23 48.5 38.5T427-266l13 106Zm42-180q58 0 99-41t41-99q0-58-41-99t-99-41q-59 0-99.5 41T342-480q0 58 40.5 99t99.5 41Zm-2-140Z"/></svg>

Before

Width:  |  Height:  |  Size: 982 B

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M396-396q-32-32-58.5-67T289-537q-5 14-6.5 28.5T281-480q0 83 58 141t141 58q14 0 28.5-2t28.5-6q-39-22-74-48.5T396-396Zm85 196q-56 0-107-21t-91-61q-40-40-61-91t-21-107q0-51 17-97.5t50-84.5q13-14 32-9.5t27 24.5q21 55 52.5 104t73.5 91q42 42 91 73.5T648-326q20 8 24.5 27t-9.5 32q-38 33-84.5 50T481-200Zm223-192q-16-5-23-20.5t-4-32.5q9-48-6-94.5T621-621q-35-35-80.5-49.5T448-677q-17 3-32-4t-21-23q-6-16 1.5-31t23.5-19q69-15 138 4.5T679-678q51 51 71 120t5 138q-4 17-19 25t-32 3ZM480-840q-17 0-28.5-11.5T440-880v-40q0-17 11.5-28.5T480-960q17 0 28.5 11.5T520-920v40q0 17-11.5 28.5T480-840Zm0 840q-17 0-28.5-11.5T440-40v-40q0-17 11.5-28.5T480-120q17 0 28.5 11.5T520-80v40q0 17-11.5 28.5T480 0Zm255-734q-12-12-12-28.5t12-28.5l28-28q11-11 27.5-11t28.5 11q12 12 12 28.5T819-762l-28 28q-12 12-28 12t-28-12ZM141-141q-12-12-12-28.5t12-28.5l28-28q12-12 28-12t28 12q12 12 12 28.5T225-169l-28 28q-11 11-27.5 11T141-141Zm739-299q-17 0-28.5-11.5T840-480q0-17 11.5-28.5T880-520h40q17 0 28.5 11.5T960-480q0 17-11.5 28.5T920-440h-40Zm-840 0q-17 0-28.5-11.5T0-480q0-17 11.5-28.5T40-520h40q17 0 28.5 11.5T120-480q0 17-11.5 28.5T80-440H40Zm779 299q-12 12-28.5 12T762-141l-28-28q-12-12-12-28t12-28q12-12 28.5-12t28.5 12l28 28q11 11 11 27.5T819-141ZM226-735q-12 12-28.5 12T169-735l-28-28q-11-11-11-27.5t11-28.5q12-12 28.5-12t28.5 12l28 28q12 12 12 28t-12 28Zm170 339Z"/></svg>

Before

Width:  |  Height:  |  Size: 1.4 KiB

View File

@@ -1,12 +0,0 @@
<!DOCTYPE html>
<html>
<head>
<title>Welcome</title>
<script src="welcome.js"></script>
</head>
<body>
This page exists to workaround an issue with Chrome that blocks permission
requests from chrome extensions
<!-- <button id="requestMicrophone">Request Microphone</button> -->
</body>
</html>

38
sync_extension.py Normal file
View File

@@ -0,0 +1,38 @@
import shutil
import os
from pathlib import Path
def sync_extension_files():
"""Copy core files from web directory to Chrome extension directory."""
web_dir = Path("whisperlivekit/web")
extension_dir = Path("chrome-extension")
files_to_sync = [
"live_transcription.html", "live_transcription.js", "live_transcription.css"
]
svg_files = [
"system_mode.svg",
"light_mode.svg",
"dark_mode.svg",
"settings.svg"
]
for file in files_to_sync:
src_path = web_dir / file
dest_path = extension_dir / file
dest_path.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(src_path, dest_path)
for svg_file in svg_files:
src_path = web_dir / "src" / svg_file
dest_path = extension_dir / "web" / "src" / svg_file
dest_path.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(src_path, dest_path)
if __name__ == "__main__":
sync_extension_files()

View File

@@ -72,6 +72,12 @@
--label-trans-text: #111111;
}
html.is-extension
{
width: 350px;
height: 500px;
}
body {
font-family: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
margin: 0;
@@ -191,6 +197,7 @@ body {
justify-content: center;
align-items: center;
gap: 15px;
position: relative;
}
.settings {
@@ -200,6 +207,52 @@ body {
gap: 12px;
}
.settings-toggle {
width: 40px;
height: 40px;
border: none;
border-radius: 50%;
background-color: var(--button-bg);
border: 1px solid var(--button-border);
cursor: pointer;
display: none;
align-items: center;
justify-content: center;
transition: all 0.2s ease;
}
.settings-toggle:hover {
background-color: var(--chip-bg);
}
.settings-toggle.active {
background-color: var(--chip-bg);
}
.settings-toggle img {
width: 20px;
height: 20px;
}
@media (max-width: 10000px) {
.settings-toggle {
display: flex;
}
.settings {
display: none;
top: 100%;
background: var(--bg);
border: 1px solid var(--border);
border-radius: 18px;
padding: 12px;
}
.settings.visible {
display: flex;
}
}
.field {
display: flex;
flex-direction: column;
@@ -454,7 +507,7 @@ label {
}
/* for smaller screens */
@media (max-width: 768px) {
@media (max-width: 200px) {
.header-container {
padding: 15px;
}

View File

@@ -5,7 +5,7 @@
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>WhisperLiveKit</title>
<link rel="stylesheet" href="/web/live_transcription.css" />
<link rel="stylesheet" href="live_transcription.css" />
</head>
<body>
@@ -23,6 +23,10 @@
</div>
</button>
<button id="settingsToggle" class="settings-toggle" title="Show/hide settings">
<img src="web/src/settings.svg" alt="Settings" />
</button>
<div class="settings">
<div class="field">
<label for="websocketInput">Websocket URL</label>
@@ -67,7 +71,7 @@
<div id="linesTranscript"></div>
</div>
<script src="/web/live_transcription.js"></script>
<script src="live_transcription.js"></script>
</body>
</html>

View File

@@ -1,4 +1,8 @@
/* Theme, WebSocket, recording, rendering logic extracted from inline script and adapted for segmented theme control and WS caption */
const isExtension = typeof chrome !== 'undefined' && chrome.runtime && chrome.runtime.getURL;
if (isExtension) {
document.documentElement.classList.add('is-extension');
}
const isWebContext = !isExtension;
let isRecording = false;
let websocket = null;
@@ -40,6 +44,21 @@ const timerElement = document.querySelector(".timer");
const themeRadios = document.querySelectorAll('input[name="theme"]');
const microphoneSelect = document.getElementById("microphoneSelect");
const settingsToggle = document.getElementById("settingsToggle");
const settingsDiv = document.querySelector(".settings");
// if (isExtension) {
// chrome.runtime.onInstalled.addListener((details) => {
// if (details.reason.search(/install/g) === -1) {
// return;
// }
// chrome.tabs.create({
// url: chrome.runtime.getURL("welcome.html"),
// active: true
// });
// });
// }
const translationIcon = `<svg xmlns="http://www.w3.org/2000/svg" height="12px" viewBox="0 -960 960 960" width="12px" fill="#5f6368"><path d="m603-202-34 97q-4 11-14 18t-22 7q-20 0-32.5-16.5T496-133l152-402q5-11 15-18t22-7h30q12 0 22 7t15 18l152 403q8 19-4 35.5T868-80q-13 0-22.5-7T831-106l-34-96H603ZM362-401 188-228q-11 11-27.5 11.5T132-228q-11-11-11-28t11-28l174-174q-35-35-63.5-80T190-640h84q20 39 40 68t48 58q33-33 68.5-92.5T484-720H80q-17 0-28.5-11.5T40-760q0-17 11.5-28.5T80-800h240v-40q0-17 11.5-28.5T360-880q17 0 28.5 11.5T400-840v40h240q17 0 28.5 11.5T680-760q0 17-11.5 28.5T640-720h-76q-21 72-63 148t-83 116l96 98-30 82-122-125Zm266 129h144l-72-204-72 204Z"/></svg>`
const silenceIcon = `<svg xmlns="http://www.w3.org/2000/svg" style="vertical-align: text-bottom;" height="14px" viewBox="0 -960 960 960" width="14px" fill="#5f6368"><path d="M514-556 320-752q9-3 19-5.5t21-2.5q66 0 113 47t47 113q0 11-1.5 22t-4.5 22ZM40-200v-32q0-33 17-62t47-44q51-26 115-44t141-18q26 0 49.5 2.5T456-392l-56-54q-9 3-19 4.5t-21 1.5q-66 0-113-47t-47-113q0-11 1.5-21t4.5-19L84-764q-11-11-11-28t11-28q12-12 28.5-12t27.5 12l675 685q11 11 11.5 27.5T816-80q-11 13-28 12.5T759-80L641-200h39q0 33-23.5 56.5T600-120H120q-33 0-56.5-23.5T40-200Zm80 0h480v-32q0-14-4.5-19.5T580-266q-36-18-92.5-36T360-320q-71 0-127.5 18T140-266q-9 5-14.5 14t-5.5 20v32Zm240 0Zm560-400q0 69-24.5 131.5T829-355q-12 14-30 15t-32-13q-13-13-12-31t12-33q30-38 46.5-85t16.5-98q0-51-16.5-97T767-781q-12-15-12.5-33t12.5-32q13-14 31.5-13.5T829-845q42 51 66.5 113.5T920-600Zm-182 0q0 32-10 61.5T700-484q-11 15-29.5 15.5T638-482q-13-13-13.5-31.5T633-549q6-11 9.5-24t3.5-27q0-14-3.5-27t-9.5-25q-9-17-8.5-35t13.5-31q14-14 32.5-13.5T700-716q18 25 28 54.5t10 61.5Z"/></svg>`;
const languageIcon = `<svg xmlns="http://www.w3.org/2000/svg" height="12" viewBox="0 -960 960 960" width="12" fill="#5f6368"><path d="M480-80q-82 0-155-31.5t-127.5-86Q143-252 111.5-325T80-480q0-83 31.5-155.5t86-127Q252-817 325-848.5T480-880q83 0 155.5 31.5t127 86q54.5 54.5 86 127T880-480q0 82-31.5 155t-86 127.5q-54.5 54.5-127 86T480-80Zm0-82q26-36 45-75t31-83H404q12 44 31 83t45 75Zm-104-16q-18-33-31.5-68.5T322-320H204q29 50 72.5 87t99.5 55Zm208 0q56-18 99.5-55t72.5-87H638q-9 38-22.5 73.5T584-178ZM170-400h136q-3-20-4.5-39.5T300-480q0-21 1.5-40.5T306-560H170q-5 20-7.5 39.5T160-480q0 21 2.5 40.5T170-400Zm216 0h188q3-20 4.5-39.5T580-480q0-21-1.5-40.5T574-560H386q-3 20-4.5 39.5T380-480q0 21 1.5 40.5T386-400Zm268 0h136q5-20 7.5-39.5T800-480q0-21-2.5-40.5T790-560H654q3 20 4.5 39.5T660-480q0 21-1.5 40.5T654-400Zm-16-240h118q-29-50-72.5-87T584-782q18 33 31.5 68.5T638-640Zm-234 0h152q-12-44-31-83t-45-75q-26 36-45 75t-31 83Zm-200 0h118q9-38 22.5-73.5T376-782q-56 18-99.5 55T204-640Z"/></svg>`
@@ -468,11 +487,35 @@ async function startRecording() {
console.log("Error acquiring wake lock.");
}
const audioConstraints = selectedMicrophoneId
? { audio: { deviceId: { exact: selectedMicrophoneId } } }
: { audio: true };
const stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
let stream;
// chromium extension. in the future, both chrome page audio and mic will be used
if (isExtension) {
try {
stream = await new Promise((resolve, reject) => {
chrome.tabCapture.capture({audio: true}, (s) => {
if (s) {
resolve(s);
} else {
reject(new Error('Tab capture failed or not available'));
}
});
});
statusText.textContent = "Using tab audio capture.";
} catch (tabError) {
console.log('Tab capture not available, falling back to microphone', tabError);
const audioConstraints = selectedMicrophoneId
? { audio: { deviceId: { exact: selectedMicrophoneId } } }
: { audio: true };
stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
statusText.textContent = "Using microphone audio.";
}
} else if (isWebContext) {
const audioConstraints = selectedMicrophoneId
? { audio: { deviceId: { exact: selectedMicrophoneId } } }
: { audio: true };
stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
}
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
@@ -657,7 +700,7 @@ function updateUI() {
statusText.textContent = "Please wait for processing to complete...";
}
} else if (isRecording) {
statusText.textContent = "Recording...";
statusText.textContent = "";
} else {
if (
statusText.textContent !== "Finished processing audio! Ready to record again." &&
@@ -691,3 +734,40 @@ navigator.mediaDevices.addEventListener('devicechange', async () => {
console.log("Error re-enumerating microphones:", error);
}
});
settingsToggle.addEventListener("click", () => {
settingsDiv.classList.toggle("visible");
settingsToggle.classList.toggle("active");
});
if (isExtension) {
async function checkAndRequestPermissions() {
const micPermission = await navigator.permissions.query({
name: "microphone",
});
const permissionDisplay = document.getElementById("audioPermission");
if (permissionDisplay) {
permissionDisplay.innerText = `MICROPHONE: ${micPermission.state}`;
}
// if (micPermission.state !== "granted") {
// chrome.tabs.create({ url: "welcome.html" });
// }
const intervalId = setInterval(async () => {
const micPermission = await navigator.permissions.query({
name: "microphone",
});
if (micPermission.state === "granted") {
if (permissionDisplay) {
permissionDisplay.innerText = `MICROPHONE: ${micPermission.state}`;
}
clearInterval(intervalId);
}
}, 100);
}
void checkAndRequestPermissions();
}

View File

@@ -33,15 +33,18 @@ def get_inline_ui_html():
with resources.files('whisperlivekit.web').joinpath('src', 'dark_mode.svg').open('r', encoding='utf-8') as f:
dark_svg = f.read()
dark_data_uri = f"data:image/svg+xml;base64,{base64.b64encode(dark_svg.encode('utf-8')).decode('utf-8')}"
with resources.files('whisperlivekit.web').joinpath('src', 'settings.svg').open('r', encoding='utf-8') as f:
settings = f.read()
settings_uri = f"data:image/svg+xml;base64,{base64.b64encode(settings.encode('utf-8')).decode('utf-8')}"
# Replace external references
html_content = html_content.replace(
'<link rel="stylesheet" href="/web/live_transcription.css" />',
'<link rel="stylesheet" href="live_transcription.css" />',
f'<style>\n{css_content}\n</style>'
)
html_content = html_content.replace(
'<script src="/web/live_transcription.js"></script>',
'<script src="live_transcription.js"></script>',
f'<script>\n{js_content}\n</script>'
)
@@ -61,6 +64,11 @@ def get_inline_ui_html():
f'<img src="{dark_data_uri}" alt="" />'
)
html_content = html_content.replace(
'<img src="web/src/settings.svg" alt="Settings" />',
f'<img src="{settings_uri}" alt="" />'
)
return html_content
except Exception as e: