一次 API 呼叫，即可取得廣東話語音

// Poll until completed — back off 2–5 s between attempts.
async function pollJob(jobId, maxAttempts = 60) {
  for (let i = 0; i < maxAttempts; i++) {
    const res = await fetch(`https://canto-gen.com/v1/audio/jobs/${jobId}`, {
      headers: { Authorization: `Bearer ${process.env.CANTOGEN_API_KEY}` },
    });
    const job = await res.json();
    if (job.status === "completed") return job; // job.audio_url is ready
    if (job.status === "failed" || job.status === "cancelled") {
      throw new Error(`job ${job.status}`);
    }
    await new Promise((r) => setTimeout(r, Math.min(2000 + i * 500, 5000)));
  }
  throw new Error("poll timeout");
}

// npm i ws   — one long-lived connection: stream tokens in, stream PCM out.
import WebSocket from "ws";

const ws = new WebSocket("wss://api.canto-gen.com/v1/audio/realtime", {
  headers: { Authorization: `Bearer ${process.env.CANTOGEN_API_KEY}` },
});

ws.on("open", () => {
  ws.send(JSON.stringify({
    type: "session.update",
    session: { voice: "sum", language: "yue", output_audio_format: "pcm16", max_session_chars: 500 },
  }));
  // One explicit utterance — or keep sending input_text.append deltas.
  ws.send(JSON.stringify({
    type: "conversation.item.create",
    item: { type: "message", content: [{ type: "input_text", text: "你好，歡迎使用港嘢！" }] },
  }));
});

const chunks = [];
ws.on("message", (raw) => {
  const ev = JSON.parse(raw.toString());
  if (ev.type === "session.created") console.log("session", ev.session.id);
  if (ev.type === "response.output_audio.delta") chunks.push(Buffer.from(ev.delta, "base64"));
  if (ev.type === "response.done") {
    // PCM16 @ 48 kHz — feed an AudioWorklet or write the chunks to disk.
    console.log("billed", ev.response.usage.billed_chars, "remaining", ev.response.usage.remaining);
    ws.close();
  }
  if (ev.type === "error") console.error(ev.error.code, ev.error.message);
});

{
  "error": "text_too_long",
  "message": "text exceeds 500 characters."
}

# OpenAPI 3.1 規格 — 直接生成你所用語言的 typed client
curl https://canto-gen.com/v1/openapi.json

# 本頁純文字 Markdown 版
curl https://canto-gen.com/v1/docs.md

# Agent 索引（llms.txt）
curl https://canto-gen.com/llms.txt