Gemini 3.8 Live

# pip install "websockets>=14"
import asyncio
import json
import os

import websockets

URL = "wss://api.modellix.ai/api/v1/live/google/gemini-3.8-live"


async def main() -> None:
    headers = {"Authorization": f"Bearer {os.environ['MODELLIX_API_KEY']}"}
    async with websockets.connect(URL, additional_headers=headers, max_size=16 * 1024 * 1024) as ws:
        # 1. The first frame must be setup.
        await ws.send(json.dumps({
            "setup": {
                "generationConfig": {"responseModalities": ["AUDIO"]},
                "outputAudioTranscription": {},
            }
        }))
        reply = json.loads(await ws.recv())
        assert "setupComplete" in reply, reply

        # 2. Send a text turn.
        await ws.send(json.dumps({"realtimeInput": {"text": "Introduce yourself in one sentence."}}))

        # 3. Read frames until the turn completes.
        async for raw in ws:
            message = json.loads(raw)
            server = message.get("serverContent") or {}
            text = (server.get("outputTranscription") or {}).get("text")
            if text:
                print(text, end="", flush=True)
            if message.get("usageMetadata"):
                print("\nUsage:", message["usageMetadata"])
            if server.get("turnComplete"):
                break


asyncio.run(main())

// npm install ws
import WebSocket from "ws";

const url = "wss://api.modellix.ai/api/v1/live/google/gemini-3.8-live";
const ws = new WebSocket(url, {
  headers: { Authorization: `Bearer ${process.env.MODELLIX_API_KEY}` },
});

ws.on("open", () => {
  // 1. The first frame must be setup.
  ws.send(JSON.stringify({
    setup: {
      generationConfig: { responseModalities: ["AUDIO"] },
      outputAudioTranscription: {},
    },
  }));
});

ws.on("message", (data) => {
  const message = JSON.parse(data.toString());
  if (message.setupComplete) {
    // 2. Send a text turn.
    ws.send(JSON.stringify({ realtimeInput: { text: "Introduce yourself in one sentence." } }));
    return;
  }
  // 3. Read frames until the turn completes.
  const text = message.serverContent?.outputTranscription?.text;
  if (text) process.stdout.write(text);
  if (message.usageMetadata) console.log("\nUsage:", message.usageMetadata);
  if (message.serverContent?.turnComplete) ws.close();
});

ws.on("close", (code, reason) => console.log(`\nClosed: ${code} ${reason}`));