add microphone picker

This commit is contained in:
Quentin Fuxa
2025-08-31 10:12:52 +02:00
parent 199e21b3ef
commit d467716e26
4 changed files with 210 additions and 59 deletions

BIN
demo.png

Binary file not shown.

Before

Width:  |  Height:  |  Size: 423 KiB

After

Width:  |  Height:  |  Size: 449 KiB

View File

@@ -184,7 +184,7 @@ body {
.settings {
display: flex;
flex-direction: column;
flex-wrap: wrap;
align-items: flex-start;
gap: 12px;
}
@@ -198,23 +198,27 @@ body {
#chunkSelector,
#websocketInput,
#themeSelector {
#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: 34px;
max-height: 30px;
}
#websocketInput {
width: 220px;
#microphoneSelect {
width: 100%;
max-width: 190px;
min-width: 120px;
}
#chunkSelector:focus,
#websocketInput:focus,
#themeSelector:focus {
#themeSelector:focus,
#microphoneSelect:focus {
outline: none;
border-color: #007bff;
box-shadow: 0 0 0 3px rgba(0, 123, 255, 0.15);
@@ -247,9 +251,9 @@ label {
}
.theme-selector-container {
position: absolute;
top: 20px;
right: 20px;
display: flex;
align-items: center;
margin-top: 17px;
}
.segmented label {
@@ -400,3 +404,57 @@ label {
font-size: 14px;
margin-bottom: 0px;
}
/* for smaller screens */
@media (max-width: 768px) {
.settings-container {
flex-direction: column;
gap: 10px;
}
.settings {
justify-content: center;
gap: 8px;
}
.field {
align-items: center;
}
#websocketInput,
#microphoneSelect {
min-width: 100px;
max-width: 160px;
}
.theme-selector-container {
margin-top: 10px;
}
}
@media (max-width: 480px) {
body {
margin: 10px;
}
.settings {
flex-direction: column;
align-items: center;
gap: 6px;
}
#websocketInput,
#microphoneSelect {
max-width: 140px;
}
.segmented label {
padding: 4px 8px;
font-size: 12px;
}
.segmented img {
width: 14px;
height: 14px;
}
}

View File

@@ -1,61 +1,73 @@
<!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" />
<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 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>
<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>
<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 class="timer">00:00</div>
</div>
</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>
</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>
<p id="status"></p>
<div id="linesTranscript"></div>
<script src="/web/live_transcription.js"></script>
<p id="status"></p>
<div id="linesTranscript"></div>
<script src="/web/live_transcription.js"></script>
</body>
</html>
</html>

View File

@@ -18,6 +18,8 @@ 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);
@@ -31,6 +33,7 @@ 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");
function getWaveStroke() {
const styles = getComputedStyle(document.documentElement);
@@ -82,6 +85,61 @@ if (darkMq && darkMq.addEventListener) {
darkMq.addListener(handleOsThemeChange);
}
async function enumerateMicrophones() {
try {
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);
@@ -377,7 +435,11 @@ async function startRecording() {
console.log("Error acquiring wake lock.");
}
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
const audioConstraints = selectedMicrophoneId
? { audio: { deviceId: { exact: selectedMicrophoneId } } }
: { audio: true };
const stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
@@ -516,3 +578,22 @@ function updateUI() {
}
recordButton.addEventListener("click", toggleRecording);
if (microphoneSelect) {
microphoneSelect.addEventListener("change", handleMicrophoneChange);
}
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);
}
});