GPT-Live 1 & OpenAI Realtime Voice APIs: Sub-300ms WebRTC Speech-to-Speech

async function initRealtimeVoiceSession() {
  // Step 1: Request ephemeral session token from your backend
  const tokenRes = await fetch("/api/session/realtime");
  const data = await tokenRes.json();
  const ephemeralKey = data.client_secret.value;

  // Step 2: Establish WebRTC peer connection
  const pc = new RTCPeerConnection();
  const audioEl = document.createElement("audio");
  audioEl.autoplay = true;
  pc.ontrack = (e) => audioEl.srcObject = e.streams[0];

  // Capture local microphone stream
  const localStream = await navigator.mediaDevices.getUserMedia({ audio: true });
  localStream.getTracks().forEach((track) => pc.addTrack(track, localStream));

  // Step 3: Negotiate SDP with OpenAI Realtime Gateway
  const offer = await pc.createOffer();
  await pc.setLocalDescription(offer);

  const sdpResponse = await fetch("https://api.apihundred.com/v1/realtime?model=gpt-live-1", {
    method: "POST",
    body: offer.sdp,
    headers: {
      Authorization: `Bearer ${ephemeralKey}`,
      "Content-Type": "application/sdp"
    }
  });

  const answer = { type: "answer", sdp: await sdpResponse.text() };
  await pc.setRemoteDescription(answer);
  console.log("GPT-Live 1 Realtime Session Connected");
}