Comfy Router リアルタイム音声セッション

# pip install websockets msgpack
import asyncio
import os

import msgpack
import websockets

URL = "wss://api.comfy.org/v2/realtime/fal/xai/grok-voice/realtime"


async def send(ws, event):
    await ws.send(msgpack.packb(event))


async def main():
    async with websockets.connect(
        URL,
        additional_headers={"X-API-Key": os.environ["COMFY_API_KEY"]},
    ) as ws:
        await send(ws, {
            "type": "session.update",
            "session": {
                "voice": "eve",
                "instructions": "You are a helpful assistant.",
                "turn_detection": {"type": "server_vad"},
            },
        })
        await send(ws, {
            "type": "conversation.item.create",
            "item": {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": "Hello!"}],
            },
        })
        await send(ws, {"type": "response.create"})

        async for message in ws:
            if isinstance(message, str):
                continue  # fal 独自の x-fal-message フレーム
            event = msgpack.unpackb(message)
            print(event["type"])
            if event["type"] == "response.done":
                break


asyncio.run(main())

// npm install ws @msgpack/msgpack
import WebSocket from "ws";
import { encode, decode } from "@msgpack/msgpack";

const ws = new WebSocket(
  "wss://api.comfy.org/v2/realtime/fal/xai/grok-voice/realtime",
  { headers: { "X-API-Key": process.env.COMFY_API_KEY } },
);

ws.on("unexpected-response", (req, res) => {
  // アップグレードが拒否されました。JSON ボディに理由が示されています。
  let body = "";
  res.on("data", (chunk) => (body += chunk));
  res.on("end", () => console.error(res.statusCode, body));
});

const send = (event) => ws.send(encode(event));

ws.on("open", () => {
  send({
    type: "session.update",
    session: {
      voice: "eve",
      instructions: "You are a helpful assistant.",
      turn_detection: { type: "server_vad" },
    },
  });
  send({
    type: "conversation.item.create",
    item: {
      type: "message",
      role: "user",
      content: [{ type: "input_text", text: "Hello!" }],
    },
  });
  send({ type: "response.create" });
});

ws.on("message", (data, isBinary) => {
  if (!isBinary) return; // fal 独自の x-fal-message フレーム
  const event = decode(data);
  console.log(event.type);
  if (event.type === "response.done") ws.close();
});

ws.on("close", (code) => console.log("closed", code));