دليل Gemini Multimodal Live API ومشروع Astra: بناء وكلاء الصوت والفيديو اللحظي

import asyncio
import websockets
import json

GEMINI_API_KEY = "YOUR_GEMINI_API_KEY"
URI = f"wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1alpha.GenerativeService.BidiGenerateContent?key={GEMINI_API_KEY}"

async def live_session():
    async with websockets.connect(URI) as ws:
        # 1. إرسال إعدادات الجلسة (Setup Message)
        setup_msg = {
            "setup": {
                "model": "models/gemini-2.5-flash",
                "generationConfig": {
                    "responseModalities": ["AUDIO", "TEXT"],
                    "speechConfig": {
                        "voiceConfig": {"prebuiltVoiceConfig": {"voiceName": "Aoede"}}
                    }
                }
            }
        }
        await ws.send(json.dumps(setup_msg))
        print("Connected to Gemini Live API!")
        
        # 2. الاستماع للردود الصوتية والنصية الحية
        while True:
            response = await ws.recv()
            data = json.loads(response)
            if "serverContent" in data:
                print("Gemini:", data["serverContent"])

asyncio.run(live_session())