Spaces:
No application file
No application file
<html lang="en"> | |
<head> | |
<meta charset="UTF-8"> | |
<meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
<title>LAHJA AI - Voice Assistant</title> | |
<script src="https://cdn.tailwindcss.com"></script> | |
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css"> | |
<style> | |
@import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&display=swap'); | |
body { | |
font-family: 'Poppins', sans-serif; | |
background: linear-gradient(135deg, #1a1a2e, #16213e); | |
color: #fff; | |
height: 100vh; | |
overflow: hidden; | |
} | |
.chat-container { | |
background: rgba(255, 255, 255, 0.1); | |
backdrop-filter: blur(10px); | |
border-radius: 20px; | |
box-shadow: 0 10px 30px rgba(0, 0, 0, 0.3); | |
border: 1px solid rgba(255, 255, 255, 0.1); | |
} | |
.message-bubble { | |
max-width: 80%; | |
padding: 12px 18px; | |
border-radius: 20px; | |
margin-bottom: 12px; | |
position: relative; | |
animation: fadeIn 0.3s ease-out; | |
} | |
.user-message { | |
background: linear-gradient(135deg, #4e54c8, #8f94fb); | |
align-self: flex-end; | |
border-bottom-right-radius: 5px; | |
} | |
.ai-message { | |
background: rgba(255, 255, 255, 0.15); | |
align-self: flex-start; | |
border-bottom-left-radius: 5px; | |
} | |
.pulse { | |
animation: pulse 1.5s infinite; | |
} | |
@keyframes pulse { | |
0% { transform: scale(1); } | |
50% { transform: scale(1.05); } | |
100% { transform: scale(1); } | |
} | |
@keyframes fadeIn { | |
from { opacity: 0; transform: translateY(10px); } | |
to { opacity: 1; transform: translateY(0); } | |
} | |
.waveform { | |
display: flex; | |
align-items: center; | |
height: 40px; | |
gap: 3px; | |
} | |
.waveform-bar { | |
background: rgba(255, 255, 255, 0.7); | |
width: 4px; | |
border-radius: 2px; | |
animation: equalize 1.5s infinite ease-in-out; | |
} | |
@keyframes equalize { | |
0%, 100% { height: 10px; } | |
50% { height: 20px; } | |
} | |
.waveform-bar:nth-child(1) { animation-delay: -0.9s; } | |
.waveform-bar:nth-child(2) { animation-delay: -0.7s; } | |
.waveform-bar:nth-child(3) { animation-delay: -0.5s; } | |
.waveform-bar:nth-child(4) { animation-delay: -0.3s; } | |
.waveform-bar:nth-child(5) { animation-delay: -0.1s; } | |
.typing-indicator { | |
display: flex; | |
align-items: center; | |
gap: 5px; | |
} | |
.typing-dot { | |
width: 8px; | |
height: 8px; | |
background: rgba(255, 255, 255, 0.7); | |
border-radius: 50%; | |
animation: typingAnimation 1.4s infinite ease-in-out; | |
} | |
.typing-dot:nth-child(1) { animation-delay: 0s; } | |
.typing-dot:nth-child(2) { animation-delay: 0.2s; } | |
.typing-dot:nth-child(3) { animation-delay: 0.4s; } | |
@keyframes typingAnimation { | |
0%, 60%, 100% { transform: translateY(0); } | |
30% { transform: translateY(-5px); } | |
} | |
.scrollbar-hide::-webkit-scrollbar { | |
display: none; | |
} | |
.scrollbar-hide { | |
-ms-overflow-style: none; | |
scrollbar-width: none; | |
} | |
</style> | |
</head> | |
<body class="flex items-center justify-center p-4"> | |
<div class="chat-container w-full max-w-2xl h-[80vh] flex flex-col"> | |
<!-- Header --> | |
<div class="p-4 border-b border-gray-700 flex items-center justify-between"> | |
<div class="flex items-center gap-3"> | |
<div class="w-10 h-10 rounded-full bg-gradient-to-r from-purple-500 to-blue-500 flex items-center justify-center"> | |
<i class="fas fa-robot text-white"></i> | |
</div> | |
<div> | |
<h2 class="font-semibold">Voice Assistant</h2> | |
<p class="text-xs text-gray-300">Powered by ChatGPT</p> | |
</div> | |
</div> | |
<div class="flex items-center gap-2"> | |
<button id="settings-btn" class="p-2 rounded-full hover:bg-gray-700 transition"> | |
<i class="fas fa-cog text-gray-300"></i> | |
</button> | |
</div> | |
</div> | |
<!-- Chat Messages --> | |
<div id="chat-messages" class="flex-1 p-4 overflow-y-auto scrollbar-hide flex flex-col"> | |
<!-- Initial welcome message --> | |
<div class="message-bubble ai-message"> | |
<p>مرحباً! أنا مساعدك الصوتي الذكي. اضغط على زر الميكروفون لبدء المحادثة معي.</p> | |
</div> | |
</div> | |
<!-- Input Area --> | |
<div class="p-4 border-t border-gray-700"> | |
<div class="flex items-center gap-2"> | |
<button id="voice-btn" class="w-14 h-14 rounded-full bg-gradient-to-r from-purple-600 to-blue-500 flex items-center justify-center text-white hover:from-purple-700 hover:to-blue-600 transition-all shadow-lg pulse"> | |
<i class="fas fa-microphone text-xl"></i> | |
</button> | |
<div class="flex-1 bg-gray-700 rounded-full px-4 py-2 flex items-center justify-between"> | |
<p id="voice-status" class="text-sm text-gray-300">اضغط على الميكروفون للتحدث</p> | |
<div id="waveform" class="waveform hidden"> | |
<div class="waveform-bar"></div> | |
<div class="waveform-bar"></div> | |
<div class="waveform-bar"></div> | |
<div class="waveform-bar"></div> | |
<div class="waveform-bar"></div> | |
</div> | |
</div> | |
</div> | |
</div> | |
</div> | |
<!-- Settings Modal --> | |
<div id="settings-modal" class="fixed inset-0 bg-black bg-opacity-50 flex items-center justify-center hidden z-50"> | |
<div class="bg-gray-800 rounded-xl p-6 w-full max-w-md"> | |
<div class="flex justify-between items-center mb-4"> | |
<h3 class="text-xl font-semibold">الإعدادات</h3> | |
<button id="close-settings" class="text-gray-400 hover:text-white"> | |
<i class="fas fa-times"></i> | |
</button> | |
</div> | |
<div class="space-y-4"> | |
<div> | |
<label class="block text-sm font-medium mb-1">Voice Model</label> | |
<select id="voiceSelect" class="w-full bg-gray-700 border border-gray-600 rounded-lg px-3 py-2 text-white"> | |
<option value="SA2">Najdi Arabic Haba v2</option> | |
<option value="us">American English</option> | |
<option value="SA1">Najdi Arabic Haba v1</option> | |
<option value="SA3">Najdi Arabic AHmmed v1</option> | |
</select> | |
</div> | |
<div> | |
<label class="block text-sm font-medium mb-1">نبرة الصوت</label> | |
<select class="w-full bg-gray-700 border border-gray-600 rounded-lg px-3 py-2 text-white"> | |
<option>ذكر</option> | |
<option>أنثى</option> | |
</select> | |
</div> | |
<div> | |
<label class="block text-sm font-medium mb-1">سرعة الصوت</label> | |
<input type="range" min="0.5" max="2" step="0.1" value="1" class="w-full"> | |
</div> | |
</div> | |
<div class="mt-6 flex justify-end gap-3"> | |
<button id="save-settings" class="px-4 py-2 bg-blue-600 rounded-lg hover:bg-blue-700 transition"> | |
حفظ الإعدادات | |
</button> | |
</div> | |
</div> | |
</div> | |
<script type="module"> | |
import {Client} from "https://cdn.jsdelivr.net/npm/@gradio/client/dist/index.min.js"; | |
// DOM Elements | |
const voiceBtn = document.getElementById('voice-btn'); | |
const voiceStatus = document.getElementById('voice-status'); | |
const waveform = document.getElementById('waveform'); | |
const chatMessages = document.getElementById('chat-messages'); | |
const settingsBtn = document.getElementById('settings-btn'); | |
const settingsModal = document.getElementById('settings-modal'); | |
const closeSettings = document.getElementById('close-settings'); | |
const saveSettings = document.getElementById('save-settings'); | |
// Speech recognition setup | |
const SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition; | |
const recognition = new SpeechRecognition(); | |
recognition.lang = 'ar-SA'; | |
recognition.interimResults = false; | |
recognition.maxAlternatives = 1; | |
// Speech synthesis setup | |
const synth = window.speechSynthesis; | |
// VITS Model Integration | |
const voiceModels = { | |
'us': 'wasmdashai/vits-en-v1', | |
'SA1': 'wasmdashai/vits-ar-sa-huba-v1', | |
'SA2': 'wasmdashai/vits-ar-sa-huba-v2', | |
'SA3': 'wasmdashai/vits-ar-sa-A', | |
}; | |
// State variables | |
let isListening = false; | |
let conversationHistory = []; | |
// Event Listeners | |
voiceBtn.addEventListener('click', toggleVoiceRecognition); | |
settingsBtn.addEventListener('click', () => settingsModal.classList.remove('hidden')); | |
closeSettings.addEventListener('click', () => settingsModal.classList.add('hidden')); | |
saveSettings.addEventListener('click', saveSettingsHandler); | |
// Functions | |
function toggleVoiceRecognition() { | |
if (isListening) { | |
stopListening(); | |
} else { | |
startListening(); | |
} | |
} | |
function startListening() { | |
isListening = true; | |
voiceBtn.classList.add('animate-pulse'); | |
voiceBtn.innerHTML = '<i class="fas fa-stop text-xl"></i>'; | |
voiceStatus.textContent = 'أنا أستمع لك...'; | |
waveform.classList.remove('hidden'); | |
try { | |
recognition.start(); | |
} catch (e) { | |
console.error('Error starting recognition:', e); | |
stopListening(); | |
} | |
} | |
function stopListening() { | |
isListening = false; | |
voiceBtn.classList.remove('animate-pulse'); | |
voiceBtn.innerHTML = '<i class="fas fa-microphone text-xl"></i>'; | |
voiceStatus.textContent = 'اضغط على الميكروفون للتحدث'; | |
waveform.classList.add('hidden'); | |
try { | |
recognition.stop(); | |
} catch (e) { | |
console.error('Error stopping recognition:', e); | |
} | |
} | |
function saveSettingsHandler() { | |
// In a real app, you would save these settings to localStorage or a backend | |
settingsModal.classList.add('hidden'); | |
showSystemMessage('تم حفظ الإعدادات بنجاح'); | |
} | |
function showSystemMessage(text) { | |
const messageDiv = document.createElement('div'); | |
messageDiv.className = 'text-center text-xs text-gray-400 my-2'; | |
messageDiv.textContent = text; | |
chatMessages.appendChild(messageDiv); | |
chatMessages.scrollTop = chatMessages.scrollHeight; | |
} | |
function addUserMessage(text) { | |
const messageDiv = document.createElement('div'); | |
messageDiv.className = 'message-bubble user-message'; | |
messageDiv.innerHTML = `<p>${text}</p>`; | |
chatMessages.appendChild(messageDiv); | |
chatMessages.scrollTop = chatMessages.scrollHeight; | |
} | |
function addAiMessage(text) { | |
const messageDiv = document.createElement('div'); | |
messageDiv.className = 'message-bubble ai-message'; | |
// Add typing indicator temporarily | |
const typingDiv = document.createElement('div'); | |
typingDiv.className = 'typing-indicator'; | |
typingDiv.innerHTML = ` | |
<div class="typing-dot"></div> | |
<div class="typing-dot"></div> | |
<div class="typing-dot"></div> | |
`; | |
messageDiv.appendChild(typingDiv); | |
chatMessages.appendChild(messageDiv); | |
chatMessages.scrollTop = chatMessages.scrollHeight; | |
// Simulate AI thinking delay | |
setTimeout(() => { | |
typingDiv.remove(); | |
messageDiv.innerHTML = `<p>${text}</p>`; | |
speakResponse(text); | |
}, 1500); | |
} | |
async function speakResponse(text) { | |
const voiceSelect = document.getElementById('voiceSelect'); | |
const voice = voiceSelect.value; | |
try { | |
const client = await Client.connect("wasmdashai/DemoLahja"); | |
const result = await client.predict("/predict", { | |
text: text, | |
name_model: voiceModels[voice], | |
speaking_rate: 1.0 | |
}); | |
const audioUrl = result.data?.[0]?.url; | |
if (audioUrl) { | |
const audio = new Audio(audioUrl); | |
audio.play(); | |
} else { | |
fallbackTTS(text); | |
} | |
} catch (err) { | |
console.error("VITS model error:", err); | |
fallbackTTS(text); | |
} | |
} | |
function fallbackTTS(text) { | |
if (synth.speaking) { | |
synth.cancel(); | |
} | |
const utterance = new SpeechSynthesisUtterance(text); | |
utterance.lang = voiceSelect.value === 'us' ? 'en-US' : 'ar-SA'; | |
utterance.rate = 1.0; | |
synth.speak(utterance); | |
} | |
function processUserInput(text) { | |
addUserMessage(text); | |
conversationHistory.push({ role: 'user', content: text }); | |
// In a real app, you would send this to your backend which connects to ChatGPT API | |
// For this demo, we'll simulate a response | |
simulateChatGPTResponse(text); | |
} | |
function simulateChatGPTResponse(userInput) { | |
// This is a simulation - in a real app, you would call the ChatGPT API | |
const responses = { | |
"مرحبا": "مرحباً بك! كيف يمكنني مساعدتك اليوم؟", | |
"كيف حالك": "أنا بخير، شكراً لسؤالك! كيف يمكنني مساعدتك؟", | |
"ما هو اسمك": "أنا مساعدك الذكي الذي يعمل بالذكاء الاصطناعي. يمكنك تسميتي كما تريد!", | |
"شكرا": "على الرحب والسعة! هل هناك أي شيء آخر تحتاج مساعدتي فيه؟", | |
"وداعا": "إلى اللقاء! لا تتردد في العودة إذا كنت بحاجة إلى أي مساعدة." | |
}; | |
const defaultResponse = "أنا آسف، لم أفهم سؤالك بالكامل. هل يمكنك توضيح ذلك؟"; | |
const response = responses[userInput.toLowerCase()] || defaultResponse; | |
setTimeout(() => { | |
addAiMessage(response); | |
conversationHistory.push({ role: 'assistant', content: response }); | |
}, 2000); | |
} | |
// Recognition event handlers | |
recognition.onresult = (event) => { | |
const speechResult = event.results[0][0].transcript; | |
processUserInput(speechResult); | |
stopListening(); | |
}; | |
recognition.onerror = (event) => { | |
console.error('Speech recognition error', event.error); | |
stopListening(); | |
if (event.error === 'not-allowed') { | |
showSystemMessage('يجب السماح باستخدام الميكروفون لتفعيل هذه الميزة'); | |
} else { | |
showSystemMessage('حدث خطأ في التعرف على الصوت. يرجى المحاولة مرة أخرى'); | |
} | |
}; | |
recognition.onend = () => { | |
if (isListening) { | |
// If we're still supposed to be listening, restart recognition | |
setTimeout(() => { | |
try { | |
recognition.start(); | |
} catch (e) { | |
console.error('Error restarting recognition:', e); | |
stopListening(); | |
} | |
}, 500); | |
} | |
}; | |
// Initialize voices when they become available | |
if (speechSynthesis.onvoiceschanged !== undefined) { | |
speechSynthesis.onvoiceschanged = () => { | |
// Voices are now loaded | |
}; | |
} | |
</script> | |
</body> | |
</html> |