GPT-Live Voix en temps réel

import fs from 'node:fs';
import WebSocket from 'ws';

const key = process.env.API_KEY;
const file = process.argv[2];
if (!key || !file) throw new Error('API_KEY et le chemin du fichier PCM sont requis');

const pcm = fs.readFileSync(file);
if (!pcm.length || pcm.length % 2) {
  throw new Error('Le PCM ne doit pas être vide et doit être aligné sur des échantillons de 16 bits');
}

const ws = new WebSocket('wss://api.agtcloud.cn/v1/live/sessions', {
  headers: { Authorization: 'Bearer ' + key },
  handshakeTimeout: 10000,
});
const audioOut = fs.createWriteStream('reply.pcm');
let started = false;
let closing = false;
let finalized = false;
let sender;
let drain;
let offset = 0;
let inputFinishedAt = 0;
let lastOutputAt = 0;

function send(event) {
  ws.send(JSON.stringify(event));
}

function closeSession(reason) {
  if (closing) return;
  closing = true;
  clearInterval(sender);
  console.error('Demande de fermeture :', reason);
  if (started && ws.readyState === WebSocket.OPEN) {
    send({ type: 'session.close' });
    drain = setTimeout(() => ws.terminate(), 15000);
  } else {
    ws.terminate();
  }
}

const limit = setTimeout(() => closeSession('Limite de 60 secondes de l’exemple'), 60000);

ws.on('open', () => send({
  type: 'session.start',
  event_id: 'start_001',
  session: {
    model: 'gpt-live-1',
    instructions: 'Répondez brièvement en chinois et attendez que l’utilisateur parle en premier.',
    audio: {
      format: { type: 'audio/pcm', rate: 24000 },
      output: { voice: 'marin' },
    },
    delegation: { type: 'client' },
  },
}));

ws.on('message', (raw) => {
  let event;
  try {
    event = JSON.parse(raw.toString());
  } catch {
    closeSession('JSON non valide');
    return;
  }

  if (event.type !== 'session.output_audio.delta') {
    console.log(raw.toString());
  }
  if (event.type === 'session.started' && !started) {
    started = true;
    sender = setInterval(() => {
      if (closing || ws.readyState !== WebSocket.OPEN) return;
      if (offset >= pcm.length) {
        inputFinishedAt ||= Date.now();
        if (
          lastOutputAt &&
          Date.now() - Math.max(lastOutputAt, inputFinishedAt) >= 3000
        ) {
          closeSession('Sortie terminée');
          return;
        }
        send({
          type: 'session.input_audio.append',
          audio: Buffer.alloc(4800).toString('base64'),
        });
        return;
      }
      const chunk = pcm.subarray(offset, offset + 4800);
      offset += chunk.length;
      send({
        type: 'session.input_audio.append',
        audio: chunk.toString('base64'),
      });
    }, 100);
  }
  if (event.type === 'session.output_audio.delta') {
    lastOutputAt = Date.now();
    audioOut.write(Buffer.from(event.delta, 'base64'));
  }
  if (event.type === 'session.output_transcript.delta') {
    lastOutputAt = Date.now();
  }
  if (event.type === 'session.closed') {
    finalized = true;
    ws.close(1000);
  }
  if (event.type === 'error') closeSession('Erreur de service');
});

ws.on('error', (error) => {
  console.error(error.message);
  closeSession('Erreur de connexion');
});

ws.on('close', (code, reason) => {
  clearTimeout(limit);
  clearTimeout(drain);
  clearInterval(sender);
  audioOut.end();
  console.error({ code, reason: reason.toString(), finalized });
  if (!finalized || code !== 1000) process.exitCode = 1;
});

process.on('SIGINT', () => closeSession('Arrêt demandé par l’utilisateur'));