Google Gemini: Gemini 3.8 Live

import { readFile, writeFile } from "node:fs/promises";
import { setTimeout as sleep } from "node:timers/promises";
import OpenAI from "openai";
import { LiveWS } from "openai/resources/live/ws";

const client = new OpenAI({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseURL: "https://api.allmodels.io/oai"
});
const live = new LiveWS(client);
const reply = [];
let quiet;

live.on("session.output_audio.delta", ({ delta }) => reply.push(Buffer.from(delta, "base64")));
live.on("session.output_transcript.delta", () => {
  // End the session two seconds after the reply's transcript goes quiet.
  clearTimeout(quiet);
  quiet = setTimeout(() => live.send({ type: "session.close" }), 2000);
});
live.on("session.closed", async () => {
  await writeFile("reply.pcm", Buffer.concat(reply));
  live.close();
});
live.on("error", console.error);

live.send({
  type: "session.start",
  session: {
    model: "gemini-3.8-live",
    audio: { format: { type: "audio/pcm", rate: 24000 }, output: { voice: "Zephyr" } },
    delegation: { type: "client" }
  }
});

// Stream 100 ms frames in real time, then two seconds of silence.
const audio = Buffer.concat([await readFile("question.pcm"), Buffer.alloc(2 * 24000 * 2)]);
for (let offset = 0; offset < audio.length; offset += 4800) {
  live.send({ type: "session.input_audio.append", audio: audio.subarray(offset, offset + 4800).toString("base64") });
  await sleep(100);
}