GPT Realtime 2.1

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

// Up to 60 seconds of mono PCM16 at 24000 Hz.
const input = await readFile("recording.pcm");
const output = createWriteStream("response.pcm"); // Mono PCM16, 24 kHz.
const url = new URL("/v1/audio/speech-to-speech/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}`, "Idempotency-Key": randomUUID() },
});
socket.on("open", () => socket.send(JSON.stringify({
  type: "session.start", model: "openai/gpt-realtime-2.1", voice: "marin",
  instructions: "Answer briefly.", max_output_tokens: 1024,
  input_audio: { "format": "pcm16", "sample_rate": 24000, channels: 1 },
  output_audio: { "format": "pcm16", "sample_rate": 24000 },
  turn_detection: { type: "none" }, input_transcription: false, output_transcription: true,
})));
socket.on("message", raw => {
  const event = JSON.parse(raw.toString());
  if (event.type === "session.ready") {
    for (let offset = 0; offset < input.length; offset += 48000)
      socket.send(input.subarray(offset, offset + 48000));
    socket.send(JSON.stringify({ type: "input_audio.commit" }));
    socket.send(JSON.stringify({ type: "response.create" }));
  } else if (event.type === "output_audio.delta") output.write(Buffer.from(event.delta, "base64"));
  else if (event.type === "response.done") socket.close();
  else if (event.type === "error") { console.error(event); socket.close(); }
});
socket.on("close", () => output.end());
socket.on("error", error => { console.error(error); output.end(); });