Speech Realtime

import WebSocket from "ws";
import { readFile } from "node:fs/promises";

// Use mono, 16 kHz, signed 16-bit little-endian PCM.
const audio = await readFile("recording.pcm");
const url = new URL("/v1/audio/transcriptions/stream", process.env.AUDIOLAB_API_URL);
url.protocol = url.protocol === "https:" ? "wss:" : "ws:";
const socket = new WebSocket(url, {
  headers: { Authorization: `Bearer ${process.env.AUDIOLAB_API_KEY}` },
});
socket.on("open", () => socket.send(JSON.stringify({
  type: "session.start", model: "azure/speech-realtime",
  encoding: "pcm_s16le", sample_rate: 16000, channels: 1,
})));
socket.on("message", (data) => {
  const event = JSON.parse(data.toString());
  console.log(event);
  if (event.type === "session.started") {
    for (let offset = 0; offset < audio.length; offset += 3200)
      socket.send(audio.subarray(offset, offset + 3200));
    socket.send(JSON.stringify({ type: "session.finish" }));
  }
});