OpenAI Realtime でローカルのブラウザー音声会話を作る

npm init -y
npm install express

import express from "express";

const app = express();
// This demo accepts only the local page, including protection against DNS rebinding.
app.use((req, res, next) => {
  const hosts = ["localhost:3000", "127.0.0.1:3000"];
  if (!hosts.includes(req.get("host"))) return res.status(403).send("Local host required");
  if (req.method === "POST" && req.get("origin") !== `http://${req.get("host")}`) {
    return res.status(403).send("Same-origin local page required");
  }
  next();
});
app.use(express.text({ type: "application/sdp", limit: "64kb" }));

app.get("/", (_req, res) => res.sendFile("index.html", { root: process.cwd() }));

app.post("/session", async (req, res) => {
  if (!process.env.OPENAI_API_KEY) return res.status(500).send("Server API key missing");
  if (typeof req.body !== "string" || !req.body.startsWith("v=")) {
    return res.status(400).send("Expected an SDP offer");
  }

  const form = new FormData();
  form.set("sdp", req.body);
  form.set("session", JSON.stringify({
    type: "realtime",
    model: "gpt-realtime-2.1",
    output_modalities: ["audio"],
    audio: { output: { voice: "marin" } },
    instructions: "Be a concise, helpful voice assistant. Do not claim access to external tools."
  }));

  try {
    const upstream = await fetch("https://api.openai.com/v1/realtime/calls", {
      method: "POST",
      headers: { Authorization: `Bearer ${process.env.OPENAI_API_KEY}` },
      body: form,
      signal: AbortSignal.timeout(25000)
    });
    const answer = await upstream.text();
    if (!upstream.ok) {
      console.error("Realtime session rejected", upstream.status);
      return res.status(502).send(`OpenAI session request failed (${upstream.status})`);
    }
    res.type("application/sdp").send(answer);
  } catch (error) {
    console.error("Realtime session network failure", error.name);
    res.status(502).send("Could not reach the Realtime API");
  }
});

app.listen(3000, "127.0.0.1", () => console.log("Open http://localhost:3000"));

<!doctype html>
<html lang="en">
<meta charset="utf-8">
<title>Local Realtime voice check</title>
<button id="start">Start voice</button>
<button id="stop" disabled>Stop</button>
<p id="status" role="status">Idle</p>
<audio id="reply" autoplay controls></audio>
<script type="module">
  const start = document.querySelector("#start");
  const stop = document.querySelector("#stop");
  const status = document.querySelector("#status");
  const reply = document.querySelector("#reply");
  let current;

  function closeSession(session = current, message = "Stopped") {
    if (!session) return;
    session.closed = true;
    clearTimeout(session.timer);
    session.abort.abort();
    session.mic?.getTracks().forEach(track => track.stop());
    if (session.pc) session.pc.onconnectionstatechange = null;
    session.dc?.close();
    session.pc?.close();
    if (current === session) {
      current = null;
      reply.srcObject = null;
      start.disabled = false;
      stop.disabled = true;
      status.textContent = message;
    }
  }

  start.onclick = async () => {
    const session = { abort: new AbortController(), closed: false };
    current = session;
    start.disabled = true;
    stop.disabled = false;
    status.textContent = "Requesting microphone";
    session.timer = setTimeout(() => closeSession(session, "Setup timed out; microphone stopped"), 30000);
    try {
      const mic = await navigator.mediaDevices.getUserMedia({ audio: true });
      if (session.closed) { mic.getTracks().forEach(track => track.stop()); return; }
      session.mic = mic;
      const pc = session.pc = new RTCPeerConnection();
      pc.ontrack = event => { if (!session.closed) reply.srcObject = event.streams[0]; };
      pc.onconnectionstatechange = () => {
        if (session.closed) return;
        status.textContent = `Connection: ${pc.connectionState}`;
        if (pc.connectionState === "connected") clearTimeout(session.timer);
        if (["failed", "closed", "disconnected"].includes(pc.connectionState)) {
          closeSession(session, "Connection ended; microphone stopped. Start a new session.");
        }
      };
      pc.addTrack(mic.getAudioTracks()[0], mic);
      const dc = session.dc = pc.createDataChannel("oai-events");
      dc.onmessage = message => {
        if (session.closed) return;
        try {
          const event = JSON.parse(message.data);
          if (event.type === "session.created") status.textContent = "Session ready: speak when connected";
          if (event.type === "response.done") {
            status.textContent = `Response status: ${event.response?.status || "unknown"}; verify audible playback`;
          }
          if (event.type === "error") closeSession(session, `Realtime error: ${event.error?.message || "unknown"}; stopped`);
        } catch { closeSession(session, "Invalid event; stopped"); }
      };
      dc.onclose = () => { if (!session.closed) closeSession(session, "Event channel closed; stopped"); };
      dc.onerror = () => closeSession(session, "Event channel failed; stopped");
      const offer = await pc.createOffer();
      await pc.setLocalDescription(offer);
      if (session.closed) return;
      // The official WebRTC example submits the generated offer directly.
      const response = await fetch("/session", {
        method: "POST",
        headers: { "Content-Type": "application/sdp" },
        body: offer.sdp,
        signal: session.abort.signal
      });
      if (!response.ok) throw new Error(await response.text());
      const answer = await response.text();
      if (session.closed) return;
      await pc.setRemoteDescription({ type: "answer", sdp: answer });
      if (!session.closed && pc.connectionState !== "connected") status.textContent = "Signaling complete; waiting for connection";
    } catch (error) {
      if (!session.closed) closeSession(session, `Start failed: ${error.message}`);
    }
  };
  stop.onclick = () => closeSession();
  window.addEventListener("pagehide", () => closeSession());
</script>
</html>

node server.mjs