ถอดเสียงบันทึกเป็นข้อความ

# Encode without line wrapping: wrapped base64 breaks the JSON string.
AUDIO=$(base64 < meeting.m4a | tr -d '\n')
# --max-time covers an hour-long recording; curl defaults to no limit.
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\"}"

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

const audio = (await readFile("meeting.m4a")).toString("base64");

const response = await fetch("https://api.paxalabs.com/v1/stt", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.PAXA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ audio, model: "paxa-stt-lite-v1-preview" }),
  // A long recording can run for minutes; give it room.
  signal: AbortSignal.timeout(300_000),
});

if (!response.ok) throw new Error(`Transcription failed: ${response.status}`);
const { text, usage } = await response.json();
console.log(text, `${usage.credits} credits`);

import base64
import os

import requests

with open("meeting.m4a", "rb") as file:
    audio = base64.b64encode(file.read()).decode()

response = requests.post(
    "https://api.paxalabs.com/v1/stt",
    headers={"Authorization": f"Bearer {os.environ['PAXA_API_KEY']}"},
    json={"audio": audio, "model": "paxa-stt-lite-v1-preview"},
    # A long recording can run for minutes; give it room.
    timeout=300,
)
response.raise_for_status()
body = response.json()
print(body["text"], body["usage"]["credits"], "credits")

{
  "text": "สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาทครบกำหนดวันที่ สิบห้า สิงหาคมนี้ชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ",
  "usage": {
    "seconds": 11.952,
    "credits": 1.66
  }
}

AUDIO=$(base64 < meeting.m4a | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\", \"timestamps\": \"word\"}"

{
  "text": "สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาทครบกำหนดวันที่ สิบห้า สิงหาคมนี้ชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ",
  "words": [
    {
      "text": "สวัสดี",
      "start": 0.12,
      "end": 0.44
    },
    {
      "text": "ค่ะ",
      "start": 0.52,
      "end": 0.66
    },
    {
      "text": "คุณ",
      "start": 1.08,
      "end": 1.24
    },
    {
      "text": "สมชาย",
      "start": 1.32,
      "end": 1.88
    },
    {
      "text": "ยอด",
      "start": 2.36,
      "end": 2.56
    },
    {
      "text": "ชำระ",
      "start": 2.6,
      "end": 2.879
    },
    {
      "text": "ของ",
      "start": 3,
      "end": 3.14
    },
    {
      "text": "ท่าน",
      "start": 3.2,
      "end": 3.359
    },
    {
      "text": "จำนวน",
      "start": 3.48,
      "end": 3.879
    },
    {
      "text": "พันสองร้อยห้าสิบ",
      "start": 4.24,
      "end": 5.4
    },
    {
      "text": "บาท",
      "start": 5.56,
      "end": 5.759
    },
    {
      "text": "ครบ",
      "start": 6.32,
      "end": 6.52
    },
    {
      "text": "กำหนด",
      "start": 6.56,
      "end": 6.84
    },
    {
      "text": "วัน",
      "start": 6.92,
      "end": 7.039
    },
    {
      "text": "ที่",
      "start": 7.04,
      "end": 7.119
    },
    {
      "text": "สิบห้า",
      "start": 7.24,
      "end": 7.48
    },
    {
      "text": "สิงหาคม",
      "start": 7.68,
      "end": 8.26
    },
    {
      "text": "นี้",
      "start": 8.36,
      "end": 8.5
    },
    {
      "text": "ชำระ",
      "start": 9.08,
      "end": 9.36
    },
    {
      "text": "ผ่าน",
      "start": 9.48,
      "end": 9.68
    },
    {
      "text": "แอป",
      "start": 9.76,
      "end": 9.92
    },
    {
      "text": "ได้",
      "start": 10,
      "end": 10.14
    },
    {
      "text": "ตลอด",
      "start": 10.2,
      "end": 10.46
    },
    {
      "text": "ยี่สิบสี่",
      "start": 10.56,
      "end": 10.96
    },
    {
      "text": "ชั่วโมง",
      "start": 11.08,
      "end": 11.4
    },
    {
      "text": "ค่ะ",
      "start": 11.52,
      "end": 11.66
    }
  ],
  "usage": {
    "seconds": 11.952,
    "credits": 1.66
  }
}

AUDIO=$(base64 < meeting.m4a | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\", \"subtitles\": \"srt\"}" \
  | jq -r .subtitles > meeting.srt

{
  "text": "สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาทครบกำหนดวันที่ สิบห้า สิงหาคมนี้ชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ",
  "subtitles": "1\n00:00:00,120 --> 00:00:01,000\nสวัสดีค่ะ\n\n2\n00:00:01,080 --> 00:00:02,080\nคุณสมชาย\n\n3\n00:00:02,360 --> 00:00:05,759\nยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาท\n\n4\n00:00:06,320 --> 00:00:08,500\nครบกำหนดวันที่ สิบห้า สิงหาคมนี้\n\n5\n00:00:09,080 --> 00:00:11,660\nชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ\n",
  "usage": {
    "seconds": 11.952,
    "credits": 1.66
  }
}

AUDIO=$(base64 < meeting.m4a | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\", \"convention\": \"written\"}"

{
  "text": "สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน 1,250 บาทครบกำหนดวันที่ 15 สิงหาคมนี้ชำระผ่านแอปได้ตลอด 24 ชั่วโมงค่ะ",
  "usage": {
    "seconds": 11.952,
    "credits": 1.66
  }
}

AUDIO=$(base64 < meeting.m4a | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\", \"diarization\": true}"

{
  "text": "สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาทครบกำหนดวันที่ สิบห้า สิงหาคมนี้ชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ",
  "segments": [
    {
      "speaker": 0,
      "text": "สวัสดีค่ะคุณสมชายยอดชำระของท่านจำนวน พันสองร้อยห้าสิบ บาทครบกำหนดวันที่ สิบห้า สิงหาคมนี้ชำระผ่านแอปได้ตลอด ยี่สิบสี่ ชั่วโมงค่ะ",
      "start": 0.12,
      "end": 11.66
    }
  ],
  "usage": {
    "seconds": 11.952,
    "credits": 1.66
  }
}

AUDIO=$(base64 < meeting.m4a | tr -d '\n')
curl -X POST https://api.paxalabs.com/v1/stt \
  --max-time 300 \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"audio\": \"$AUDIO\", \"model\": \"paxa-stt-lite-v1-preview\", \"language\": \"th\", \"vocabulary\": [\"Paxa Labs\", \"quarterly review\"]}"

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}