點樣起你個端點。

# A Cantonese Voice Benchmark endpoint, in about forty lines.
# python -m pip install websockets
# python server.py      →  ws://0.0.0.0:8080
#
# Put your recogniser in transcribe(). Everything else is the protocol.
import asyncio, json, os
from websockets.asyncio.server import serve

CHUNK = 3200  # bytes per frame we receive: 100ms of 16kHz mono s16le


def transcribe(pcm: bytes) -> str:
    """Raw 16kHz mono signed 16-bit PCM. No WAV header — we strip it."""
    return "你好"  # ← your model here


async def handle(ws):
    audio = bytearray()
    async for message in ws:
        # Binary frames are the caller's voice, arriving while they speak.
        if isinstance(message, (bytes, bytearray)):
            audio.extend(message)
            continue

        frame = json.loads(message)

        if frame["type"] == "hello":
            # Nothing is streamed until you answer this. An endpoint that
            # stays silent here is failed as an incomplete handshake.
            await ws.send(json.dumps({"type": "ready", "accept": "pcm_s16le_16k"}))

        elif frame["type"] == "end_of_utterance":
            # The deadline clock starts at this frame, not at hello.
            text = transcribe(bytes(audio))
            await ws.send(json.dumps({"type": "transcript", "text": text}))
            return  # one clip per connection


async def main():
    async with serve(handle, "0.0.0.0", int(os.environ.get("PORT", 8080))):
        await asyncio.get_running_loop().create_future()

asyncio.run(main())

// A Cantonese Voice Benchmark endpoint, in about forty lines.
// npm i ws  &&  node server.mjs      →  ws://0.0.0.0:8080
//
// Put your recogniser in transcribe(). Everything else is the protocol.
import { WebSocketServer } from 'ws';

const CHUNK = 3200; // bytes per frame we send: 100ms of 16kHz mono s16le

/** Raw 16kHz mono signed 16-bit PCM. No WAV header — we strip it. */
function transcribe(pcm) {
  return '你好'; // ← your model here
}

const wss = new WebSocketServer({ port: Number(process.env.PORT ?? 8080) });

wss.on('connection', (ws) => {
  const audio = [];

  ws.on('message', async (data, isBinary) => {
    // Binary frames are the caller's voice, arriving while they speak.
    if (isBinary) { audio.push(data); return; }

    const frame = JSON.parse(data.toString());

    if (frame.type === 'hello') {
      // Nothing is streamed until you answer this. An endpoint that stays
      // silent here is failed as an incomplete handshake.
      ws.send(JSON.stringify({ type: 'ready', accept: 'pcm_s16le_16k' }));
    }

    if (frame.type === 'end_of_utterance') {
      // The deadline clock starts at this frame, not at hello.
      const text = transcribe(Buffer.concat(audio));
      ws.send(JSON.stringify({ type: 'transcript', text }));
      ws.close();
    }
  });
});