import WebSocket from "ws";

const ws = new WebSocket("wss://app.voho.ai/v1/speech/ws", {
  headers: { Authorization: `Bearer ${process.env.VOHO_API_KEY}` },
});

const chunks = [];

ws.on("message", (data, isBinary) => {
  if (isBinary) {
    chunks.push(data);            // audio
    return;
  }
  const msg = JSON.parse(data.toString());

  if (msg.type === "ready") {
    ws.send(JSON.stringify({ type: "start", voice: "layla", format: "opus" }));
  }

  if (msg.type === "started") {
    // Text as it becomes available — e.g. tokens from an LLM.
    ws.send(JSON.stringify({ type: "text", text: "أهلاً بك في فوهو، " }));
    ws.send(JSON.stringify({ type: "text", text: "كيف أقدر أساعدك؟" }));
    ws.send(JSON.stringify({ type: "flush" }));
  }

  if (msg.type === "done") {
    console.log(msg.characters, "chars", msg.cost_cents, "cents");
    ws.close();
  }

  if (msg.type === "error") {
    console.error(msg.error.code, msg.error.message);
    ws.close();
  }
});

import json, websockets, asyncio

async def speak():
    url = "wss://app.voho.ai/v1/speech/ws"
    headers = {"Authorization": f"Bearer {API_KEY}"}
    chunks = []

    async with websockets.connect(url, additional_headers=headers) as ws:
        async for raw in ws:
            if isinstance(raw, bytes):
                chunks.append(raw)
                continue

            msg = json.loads(raw)
            if msg["type"] == "ready":
                await ws.send(json.dumps(
                    {"type": "start", "voice": "layla", "format": "opus"}))
            elif msg["type"] == "started":
                await ws.send(json.dumps({"type": "text", "text": "أهلاً بك، "}))
                await ws.send(json.dumps({"type": "text", "text": "كيف أساعدك؟"}))
                await ws.send(json.dumps({"type": "flush"}))
            elif msg["type"] == "done":
                print(msg["characters"], "chars", msg["cost_cents"], "cents")
                break
            elif msg["type"] == "error":
                raise RuntimeError(msg["error"]["message"])

    open("out.ogg", "wb").write(b"".join(chunks))

asyncio.run(speak())