跳到主要内容

Introducing Kaitom Voice V3 - Next-Generation Thai Text-to-Speech

· 5 分钟阅读
Kobkrit Viriyayudhakorn
CEO @ iApp Technology

Kaitom Voice V3 - Next-Generation Thai Text-to-Speech

We're excited to announce Kaitom Voice V3, the next generation of our Thai Text-to-Speech API. This major update brings significant improvements to speech quality, introduces smart text normalization, and simplifies integration with a modern JSON-based API.

What's New in V3​

Kaitom Voice V3 represents a complete overhaul of our TTS engine, delivering the most natural-sounding Thai speech synthesis we've ever created.

Smart Text Normalization​

V3 automatically handles complex text elements that previously required pre-processing:

TypeInputSpoken Output
Numbers1,234.56"หนึ่งพันสองร้อยสามสิบสี่จุดห้าหก"
Dates27/01/2569"วันที่ยี่สิบเจ็ดมกราคมพ.ศ.สองพันห้าร้อยหกสิบเก้า"
Currency฿1,500"หนึ่งพันห้าร้อยบาท"
Time14:30"สิบสี่นาฬิกาสามสิบนาที"
Percentages25%"ยี่สิบห้าเปอร์เซ็นต์"

Automatic Language Detection​

No more specifying language modes! V3 automatically detects and handles Thai-English mixed content:

Hello and Welcome! ยินดีต้อนรับสู่ iApp Technology ผู้นำด้าน AI ของประเทศไทย

Simplified JSON API​

We've modernized the API with a clean JSON interface:

curl -X POST 'https://api.iapp.co.th/v3/store/audio/tts' \
--header 'apikey: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{"text": "สวัสดีครับ น้องไข่ต้ม เวอร์ชั่น 3"}'

Streaming Audio Output​

  • 24 kHz mono PCM streamed — start playback as soon as bytes arrive
  • Real-time factor ~0.3–0.5 — 10 s of audio synthesized in 3–5 s
  • Up to ~1,000 Thai characters per request (longer text auto-chunks server-side)
  • Wrap with a WAV header (44-byte) on the client to play or save as .wav

NEW: Thai Voice Cloning​

V3 introduces voice cloning for Thai as a separate endpoint. Provide an 8–12 second clean Thai voice clip plus its literal transcript, and the synthesized speech will mimic that voice:

curl -X POST 'https://api.iapp.co.th/v3/store/audio/tts/clone' \
--header 'apikey: YOUR_API_KEY' \
--form 'text=สวัสดีครับ วันนี้ทดสอบการโคลนเสียง' \
--form 'speed=1.0' \
--form 'ref_text=ฮัลโหล สวัสดีครับ ผมชื่อไข่ต้ม' \
--form 'ref_audio=@reference.wav' \
--output 'output.pcm'

Voice cloning currently supports Thai language only. See the interactive cloning demo to record yourself and try it in the browser.

Quick Start​

Python​

import requests

url = "https://api.iapp.co.th/v3/store/audio/tts"
headers = {
"apikey": "YOUR_API_KEY",
"Content-Type": "application/json"
}
data = {"text": "สวัสดีครับ น้องไข่ต้ม เวอร์ชั่น 3"}

response = requests.post(url, headers=headers, json=data)
with open("output.wav", "wb") as f:
f.write(response.content)

JavaScript​

const response = await fetch("https://api.iapp.co.th/v3/store/audio/tts", {
method: "POST",
headers: {
"apikey": "YOUR_API_KEY",
"Content-Type": "application/json"
},
body: JSON.stringify({ text: "สวัสดีครับ น้องไข่ต้ม เวอร์ชั่น 3" })
});
const blob = await response.blob();

V3 vs V2 Comparison​

FeatureV2V3
API FormatForm DataJSON
Language ModeRequired (TH / TH_MIX_EN)Auto-detected
Text NormalizationBasicSmart (numbers, dates, currency)
Max CharactersUnlimited10,000
Audio QualityStandard24 kHz streamed PCM

Pricing​

V3 pricing:

  • /v3/store/audio/tts (default Kaitom voice) — 1 IC per 400 chars
  • /v3/store/audio/tts/clone (Thai voice cloning) — 1 IC per 400 chars

Use Cases​

E-Learning & Education​

Convert educational content into audio lessons with proper pronunciation of numbers, dates, and technical terms.

Chatbots & Virtual Assistants​

Create natural-sounding voice responses for Thai chatbots with automatic language handling.

Content Creation​

Generate professional voiceovers for videos and podcasts with high-quality audio output.

Accessibility​

Make digital content accessible to visually impaired users with clear, natural speech.

IVR Systems​

Build interactive voice response systems with smart text normalization for phone numbers, amounts, and dates.

Migration Guide​

Migrating from V2 to V3 is straightforward:

Before (V2):

curl -X POST 'https://api.iapp.co.th/v3/store/speech/text-to-speech/kaitom' \
--header 'apikey: YOUR_API_KEY' \
--form 'text="สวัสดีครับ"' \
--form 'language="TH"'

After (V3):

curl -X POST 'https://api.iapp.co.th/v3/store/audio/tts' \
--header 'apikey: YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{"text": "สวัสดีครับ"}'

Key changes:

  1. New endpoint: /v3/store/audio/tts
  2. Content-Type: application/json
  3. Request body: JSON format {"text": "..."}
  4. No language parameter needed

Try It Now​

Ready to experience the next generation of Thai TTS?

What's Next​

We're continuously improving Kaitom Voice. Upcoming features include:

  • Additional voice options (coming soon)
  • SSML support for fine-grained control
  • Voice cloning for English and other languages

Feedback​

We'd love to hear your feedback on Kaitom Voice V3! Join our community:


Kaitom Voice V3 is available now for all iApp API users. Existing V1 and V2 APIs will continue to be supported.