リアルタイム Speech-to-Text クイックスタート

import Cartesia from "@cartesia/cartesia-js";

const apiKey = process.env["CARTESIA_API_KEY"];
if (!apiKey) {
  throw new Error("Set CARTESIA_API_KEY first.");
}

const client = new Cartesia({ apiKey });

const ttsResponse = await client.tts.generate({
  model_id: "sonic-3.5",
  transcript: "Hello from Cartesia. This is a realtime STT quickstart.",
  voice: { mode: "id", id: "694f9389-aac1-45b6-b726-9d9369183238" },
  output_format: { container: "raw", encoding: "pcm_s16le", sample_rate: 16000 },
  language: "en",
});

const audio = Buffer.from(await ttsResponse.arrayBuffer());
const chunkSize = 3200; // 100ms of 16kHz pcm_s16le mono audio

console.log("Sending audio chunks to Cartesia's Ink-2 model...");
const ws = client.stt.autoFinalize.websocket({
  model: "ink-2",
  encoding: "pcm_s16le",
  sample_rate: 16000,
});

const sender = (async () => {
  for (let i = 0; i < audio.length; i += chunkSize) {
    ws.sendRaw(audio.subarray(i, i + chunkSize));
    await new Promise((resolve) => setTimeout(resolve, 100));
  }
  // We recommend draining the audio as per
  // https://docs.cartesia.ai/use-the-api/stt/turns#draining-events
  ws.send({ type: "close" });
})();

for await (const event of ws.stream()) {
  if (event.type === "message") {
    if (event.message.type === "turn.update") {
      console.log(`turn.update: ${event.message.transcript}`);
    } else if (event.message.type === "turn.end") {
      console.log(`turn.end: ${event.message.transcript}`);
    } else if (event.message.type === "error") {
      throw new Error(event.message.message);
    }
  } else if (event.type === "error") {
    throw event.error;
  }
}

await sender;