feat: web frontend with voice selector, transcript, LiveKit client
This commit is contained in:
Shane
+172
@@ -0,0 +1,172 @@
|
||||
// Voice Assistant — LiveKit client
|
||||
const { Room, RoomEvent, RemoteParticipant, AudioPlaybackStats } = LivekitClient;
|
||||
|
||||
// ── Config (injected from environment at build time, or hardcoded for LAN) ──
|
||||
const LIVEKIT_URL = `ws://${window.location.hostname}:7880`;
|
||||
const API_KEY = "devkey";
|
||||
const ROOM_NAME = "voice-room";
|
||||
const AGENT_NAME = "voice-assistant";
|
||||
|
||||
// ── State ──
|
||||
let room = null;
|
||||
let agentParticipant = null;
|
||||
|
||||
// ── DOM ──
|
||||
const startBtn = document.getElementById("startBtn");
|
||||
const stopBtn = document.getElementById("stopBtn");
|
||||
const statusEl = document.getElementById("status");
|
||||
const messagesEl = document.getElementById("messages");
|
||||
const voiceSelect = document.getElementById("voiceSelect");
|
||||
|
||||
// ── Voice switching ──
|
||||
voiceSelect.addEventListener("change", () => {
|
||||
const voice = voiceSelect.value;
|
||||
if (room && agentParticipant) {
|
||||
// Send data message to agent to switch voice
|
||||
room.localParticipant.publishData(
|
||||
JSON.stringify({ type: "set_voice", voice }).encodeInto(new Uint8Array()),
|
||||
[agentParticipant]
|
||||
);
|
||||
addMessage("system", `Voice changed to ${voice}`);
|
||||
} else {
|
||||
// Save preference for next session
|
||||
localStorage.setItem("preferred_voice", voice);
|
||||
}
|
||||
});
|
||||
|
||||
// Restore saved voice preference
|
||||
const savedVoice = localStorage.getItem("preferred_voice");
|
||||
if (savedVoice) {
|
||||
voiceSelect.value = savedVoice;
|
||||
}
|
||||
|
||||
// ── Start ──
|
||||
startBtn.addEventListener("click", async () => {
|
||||
try {
|
||||
statusEl.textContent = "Connecting...";
|
||||
|
||||
room = new Room({
|
||||
adaptiveStream: true,
|
||||
dynacast: true,
|
||||
});
|
||||
|
||||
// Listen for transcripts from the agent
|
||||
room.on(RoomEvent.ParticipantConnected, (participant) => {
|
||||
if (participant.identity === AGENT_NAME || participant.kind === "agent") {
|
||||
agentParticipant = participant;
|
||||
statusEl.textContent = "Agent connected";
|
||||
|
||||
// Send current voice selection
|
||||
const voice = voiceSelect.value;
|
||||
room.localParticipant.publishData(
|
||||
JSON.stringify({ type: "set_voice", voice }).encodeInto(new Uint8Array()),
|
||||
[participant]
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
room.on(RoomEvent.DataReceived, (payload, participant) => {
|
||||
try {
|
||||
const msg = JSON.parse(payload.decodeToString());
|
||||
if (msg.type === "transcript") {
|
||||
addMessage(msg.role || "agent", msg.text);
|
||||
}
|
||||
} catch (e) {
|
||||
// Ignore non-JSON data
|
||||
}
|
||||
});
|
||||
|
||||
room.on(RoomEvent.ConnectionQualityChanged, (participant, quality) => {
|
||||
if (participant === room.localParticipant) {
|
||||
statusEl.textContent = `Connected (${quality} quality)`;
|
||||
}
|
||||
});
|
||||
|
||||
room.on(RoomEvent.Disconnected, () => {
|
||||
statusEl.textContent = "Disconnected";
|
||||
startBtn.disabled = false;
|
||||
stopBtn.disabled = true;
|
||||
});
|
||||
|
||||
await room.connect(LIVEKIT_URL, {
|
||||
accessToken: generateToken(),
|
||||
autoSubscribe: true,
|
||||
});
|
||||
|
||||
// Request agent join
|
||||
await requestAgentJoin();
|
||||
|
||||
statusEl.textContent = "Connected — speak now";
|
||||
startBtn.disabled = true;
|
||||
stopBtn.disabled = false;
|
||||
|
||||
} catch (err) {
|
||||
console.error("Connection failed:", err);
|
||||
statusEl.textContent = `Error: ${err.message}`;
|
||||
}
|
||||
});
|
||||
|
||||
// ── Stop ──
|
||||
stopBtn.addEventListener("click", () => {
|
||||
if (room) {
|
||||
room.disconnect();
|
||||
room = null;
|
||||
agentParticipant = null;
|
||||
}
|
||||
statusEl.textContent = "Disconnected";
|
||||
startBtn.disabled = false;
|
||||
stopBtn.disabled = true;
|
||||
});
|
||||
|
||||
// ── Helper: generate a LiveKit access token (simplified for LAN dev) ──
|
||||
// In production, this would be done server-side. For LAN dev, we use a static token.
|
||||
function generateToken() {
|
||||
// The LiveKit server with devkey/devsecret will accept any token signed with that key.
|
||||
// For simplicity in this LAN setup, we'll let the server handle auth.
|
||||
return "dev-token";
|
||||
}
|
||||
|
||||
// ── Helper: request agent to join the room ──
|
||||
async function requestAgentJoin() {
|
||||
// Send a data message to trigger agent dispatch
|
||||
if (room && room.localParticipant) {
|
||||
const msg = JSON.stringify({ type: "join_agent", agent: AGENT_NAME });
|
||||
room.localParticipant.publishData(
|
||||
msg.encodeInto(new Uint8Array()),
|
||||
[] // broadcast to all participants
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// ── Helper: add a message to the transcript ──
|
||||
function addMessage(role, text) {
|
||||
const div = document.createElement("div");
|
||||
div.className = `message ${role}`;
|
||||
div.innerHTML = `<span class="role">${role === "user" ? "You" : role === "agent" ? "Assistant" : "System"}</span> ${text}`;
|
||||
messagesEl.appendChild(div);
|
||||
messagesEl.scrollTop = messagesEl.scrollHeight;
|
||||
}
|
||||
|
||||
// ── Capture user speech for transcript display ──
|
||||
// We'll use the Web Speech API as a fallback for showing what the user said.
|
||||
// The actual STT is handled by the agent's Azure STT pipeline.
|
||||
let recognition = null;
|
||||
if ("webkitSpeechRecognition" in window || "SpeechRecognition" in window) {
|
||||
const SpeechRec = window.SpeechRecognition || window.webkitSpeechRecognition;
|
||||
recognition = new SpeechRec();
|
||||
recognition.continuous = true;
|
||||
recognition.interimResults = true;
|
||||
recognition.lang = "en-US";
|
||||
|
||||
recognition.onresult = (event) => {
|
||||
for (let i = event.resultIndex; i < event.results.length; i++) {
|
||||
if (event.results[i].isFinal) {
|
||||
addMessage("user", event.results[i][0].transcript);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// Start/stop recognition with the room connection
|
||||
const origConnect = Room.prototype.connect;
|
||||
// We'll start recognition when room connects
|
||||
}
|
||||
@@ -0,0 +1,50 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Voice Assistant</title>
|
||||
<link rel="stylesheet" href="style.css">
|
||||
</head>
|
||||
<body>
|
||||
<div class="container">
|
||||
<header>
|
||||
<h1>Voice Assistant</h1>
|
||||
<p class="subtitle">Azure Speech + Gemma LLM, real-time conversation</p>
|
||||
</header>
|
||||
|
||||
<div class="controls">
|
||||
<button id="startBtn" class="btn btn-primary">Start Conversation</button>
|
||||
<button id="stopBtn" class="btn btn-danger" disabled>Stop</button>
|
||||
</div>
|
||||
|
||||
<div class="voice-panel">
|
||||
<label for="voiceSelect">Voice:</label>
|
||||
<select id="voiceSelect">
|
||||
<option value="en-US-AvaNeural" selected>Ava (DragonHD)</option>
|
||||
<option value="en-US-JennyNeural">Jenny</option>
|
||||
<option value="en-US-GuyNeural">Guy</option>
|
||||
<option value="en-US-AndrewNeural">Andrew</option>
|
||||
<option value="en-US-AriaNeural">Aria</option>
|
||||
<option value="en-US-EmmaNeural">Emma</option>
|
||||
<option value="en-US-EricNeural">Eric</option>
|
||||
<option value="en-US-BrianNeural">Brian</option>
|
||||
<option value="en-US-AshleyNeural">Ashley</option>
|
||||
<option value="en-US-RichardNeural">Richard</option>
|
||||
<option value="en-US-TinaNeural">Tina</option>
|
||||
<option value="en-US-SteffanNeural">Steffan</option>
|
||||
</select>
|
||||
</div>
|
||||
|
||||
<div class="status" id="status">Disconnected</div>
|
||||
|
||||
<div class="transcript" id="transcript">
|
||||
<div class="transcript-header">Conversation</div>
|
||||
<div id="messages"></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/index.umd.min.js"></script>
|
||||
<script src="app.js"></script>
|
||||
</body>
|
||||
</html>
|
||||
+173
@@ -0,0 +1,173 @@
|
||||
* { margin: 0; padding: 0; box-sizing: border-box; }
|
||||
|
||||
body {
|
||||
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
|
||||
background: #0f1117;
|
||||
color: #e4e4e7;
|
||||
min-height: 100vh;
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
align-items: flex-start;
|
||||
padding: 2rem 1rem;
|
||||
}
|
||||
|
||||
.container {
|
||||
width: 100%;
|
||||
max-width: 680px;
|
||||
}
|
||||
|
||||
header {
|
||||
text-align: center;
|
||||
margin-bottom: 2rem;
|
||||
}
|
||||
|
||||
h1 {
|
||||
font-size: 2rem;
|
||||
font-weight: 700;
|
||||
background: linear-gradient(135deg, #60a5fa, #a78bfa);
|
||||
-webkit-background-clip: text;
|
||||
-webkit-text-fill-color: transparent;
|
||||
}
|
||||
|
||||
.subtitle {
|
||||
color: #71717a;
|
||||
margin-top: 0.5rem;
|
||||
font-size: 0.9rem;
|
||||
}
|
||||
|
||||
.controls {
|
||||
display: flex;
|
||||
gap: 1rem;
|
||||
justify-content: center;
|
||||
margin-bottom: 1.5rem;
|
||||
}
|
||||
|
||||
.btn {
|
||||
padding: 0.75rem 2rem;
|
||||
border: none;
|
||||
border-radius: 8px;
|
||||
font-size: 1rem;
|
||||
font-weight: 600;
|
||||
cursor: pointer;
|
||||
transition: all 0.2s;
|
||||
}
|
||||
|
||||
.btn:disabled {
|
||||
opacity: 0.4;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
.btn-primary {
|
||||
background: #3b82f6;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.btn-primary:hover:not(:disabled) {
|
||||
background: #2563eb;
|
||||
transform: translateY(-1px);
|
||||
}
|
||||
|
||||
.btn-danger {
|
||||
background: #ef4444;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.btn-danger:hover:not(:disabled) {
|
||||
background: #dc2626;
|
||||
}
|
||||
|
||||
.voice-panel {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 0.75rem;
|
||||
justify-content: center;
|
||||
margin-bottom: 1.5rem;
|
||||
padding: 1rem;
|
||||
background: #1c1e26;
|
||||
border-radius: 8px;
|
||||
}
|
||||
|
||||
.voice-panel label {
|
||||
font-weight: 600;
|
||||
color: #a1a1aa;
|
||||
}
|
||||
|
||||
.voice-panel select {
|
||||
padding: 0.5rem 1rem;
|
||||
background: #27272a;
|
||||
color: #e4e4e7;
|
||||
border: 1px solid #3f3f46;
|
||||
border-radius: 6px;
|
||||
font-size: 0.9rem;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.voice-panel select:focus {
|
||||
outline: none;
|
||||
border-color: #3b82f6;
|
||||
}
|
||||
|
||||
.status {
|
||||
text-align: center;
|
||||
padding: 0.75rem;
|
||||
background: #1c1e26;
|
||||
border-radius: 8px;
|
||||
margin-bottom: 1.5rem;
|
||||
font-size: 0.9rem;
|
||||
color: #a1a1aa;
|
||||
}
|
||||
|
||||
.transcript {
|
||||
background: #1c1e26;
|
||||
border-radius: 8px;
|
||||
padding: 1rem;
|
||||
max-height: 50vh;
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
.transcript-header {
|
||||
font-weight: 700;
|
||||
color: #a1a1aa;
|
||||
margin-bottom: 1rem;
|
||||
font-size: 0.85rem;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 0.05em;
|
||||
}
|
||||
|
||||
.message {
|
||||
padding: 0.6rem 0.8rem;
|
||||
margin-bottom: 0.5rem;
|
||||
border-radius: 6px;
|
||||
font-size: 0.95rem;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
.message.user {
|
||||
background: #1e3a5f;
|
||||
border-left: 3px solid #3b82f6;
|
||||
}
|
||||
|
||||
.message.agent {
|
||||
background: #2d1f4e;
|
||||
border-left: 3px solid #a78bfa;
|
||||
}
|
||||
|
||||
.message.system {
|
||||
background: #27272a;
|
||||
color: #71717a;
|
||||
font-style: italic;
|
||||
font-size: 0.85rem;
|
||||
}
|
||||
|
||||
.role {
|
||||
font-weight: 700;
|
||||
margin-right: 0.5rem;
|
||||
}
|
||||
|
||||
.message.user .role { color: #60a5fa; }
|
||||
.message.agent .role { color: #a78bfa; }
|
||||
|
||||
/* Scrollbar */
|
||||
.transcript::-webkit-scrollbar { width: 6px; }
|
||||
.transcript::-webkit-scrollbar-track { background: transparent; }
|
||||
.transcript::-webkit-scrollbar-thumb { background: #3f3f46; border-radius: 3px; }
|
||||
Reference in New Issue
Block a user