ถอดเสียงสดภาษาไทย

import { open } from "node:fs/promises";

// Runs on Bun as-is; on Node, `import WebSocket from "ws"` accepts
// the same constructor options. Browsers cannot send this header, and
// API keys never ship to browsers anyway: relay the audio through your
// server.
const socket = new WebSocket("wss://api.paxalabs.com/v1/stt/live", {
  headers: { Authorization: `Bearer ${process.env.PAXA_API_KEY}` },
});

socket.onopen = async () => {
  socket.send(JSON.stringify({
    type: "start",
    model: "paxa-stt-lite-realtime-v1-preview",
    audio: { encoding: "pcm_s16le", sample_rate: 16000 },
    language: "th",
  }));
  // 16 kHz signed 16-bit mono is 32,000 bytes a second. A microphone
  // delivers frames at this pace on its own; a file has to be paced.
  const file = await open("caller.pcm");
  const frame = new Uint8Array(640); // 20 ms
  for (;;) {
    const { bytesRead } = await file.read(frame, 0, frame.length);
    if (bytesRead === 0) break;
    socket.send(frame.subarray(0, bytesRead));
    await new Promise((resolve) => setTimeout(resolve, 20));
  }
  socket.send(JSON.stringify({ type: "end" }));
};

socket.onmessage = (event) => {
  const message = JSON.parse(String(event.data));
  switch (message.type) {
    case "speech_started":
      // The user is talking: stop the agent's audio, cancel its reply.
      break;
    case "transcript":
      if (message.is_final) console.log(`turn ${message.turn}: ${message.text}`);
      break;
    case "done":
      socket.close();
  }
};

import json
import os
import time

from websockets.sync.client import connect  # pip install websockets

with connect(
    "wss://api.paxalabs.com/v1/stt/live",
    additional_headers={"Authorization": f"Bearer {os.environ['PAXA_API_KEY']}"},
) as socket:
    socket.send(json.dumps({
        "type": "start",
        "model": "paxa-stt-lite-realtime-v1-preview",
        "audio": {"encoding": "pcm_s16le", "sample_rate": 16000},
        "language": "th",
    }))
    # 16 kHz signed 16-bit mono is 32,000 bytes a second; a file has to
    # be paced the way a microphone paces itself.
    with open("caller.pcm", "rb") as audio:
        while frame := audio.read(640):  # 20 ms
            socket.send(frame)
            time.sleep(0.02)
    socket.send(json.dumps({"type": "end"}))

    for message in socket:
        event = json.loads(message)
        if event["type"] == "transcript" and event["is_final"]:
            print(event["turn"], event["text"])
        elif event["type"] == "done":
            break

{"type":"started","connection":"7d9c2b7e-4a41-4c8e-9a35-1f26d8c04b7a","model":"paxa-stt-lite-realtime-v1-preview"}
{"type":"speech_started","turn":1,"time":0.3}
{"type":"speech_ended","turn":1,"time":12.252}
{"type":"charged","seq":1,"seconds":12.252,"credits":2.56,"total_credits":2.56}
{"type":"transcript","turn":1,"is_final":true,"text":"สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาทครบกำหนดวันที่ สิบห้า สิงหาคมนี้ชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ","start":0.3,"end":12.252}
{"type":"done","total_seconds":12.252,"turns":1,"total_credits":2.56}