Skip to main content

🗣️ Thai Text-to-Speech (TTS)

1 ICper 400 characters
Active POST /v3/store/audio/tts/generate

Welcome to Thai Text-to-Speech API documentation. Our AI-powered service converts Thai and English text into natural-sounding speech with high accuracy and speed.

iApp Text to Speech API

Choose Your Version​

We offer three versions of our Text-to-Speech API to meet different needs:

🚀 Version 3 (Recommended) NEW​

Next-generation TTS with smart features

  • Voice: Kaitom V3 (น้องไข่ต้ม เวอร์ชั่น 3)
  • Method: POST with JSON body
  • Output: WAV format (24 kHz)
  • Special Features:
    • Smart text normalization (numbers, dates, currency)
    • Automatic Thai-English language detection
    • Extended 10,000 character limit
    • Simplified JSON API

📖 View V3 Documentation →

🔹 Version 2 (Stable)​

Enhanced quality with POST-based API

  • Voice: Kaitom V2 (น้องไข่ต้ม เวอร์ชั่น 2)
  • Method: POST with Form Data
  • Output: WAV format
  • Special Features:
    • Improved speech naturalness
    • Language mode selection (TH / TH_MIX_EN)
    • Better Thai-English mixing
    • Enhanced pronunciation

📖 View V2 Documentation →

📱 Version 1 (Legacy)​

Simple GET-based API with multiple voices

  • Voices:
    • Kaitom V1 (เสียงน้องไข่ต้ม)
    • Cee (เสียงคุณซี @ceemeagain)
  • Method: GET
  • Output: MP3/WAV format
  • Special Features:
    • Simple URL-based requests
    • Two voice options
    • Celebrity voice (Cee)

📖 View V1 Documentation →

Quick Comparison​

FeatureV1 (Legacy)V2 (Stable)V3 (Recommended)
API MethodGETPOST (Form Data)POST (JSON)
Voice OptionsKaitom V1, CeeKaitom V2Kaitom V3
Speech QualityGoodEnhancedBest ✨
Mixed LanguageSupportedImprovedAuto-detected ✨
Language ModeAuto-detectSelectableNot needed ✨
Text NormalizationBasicBasicSmart (numbers, dates, currency) ✨
Max CharactersNo limitNo limit10,000
Output FormatMP3/WAVWAVWAV (24 kHz)
IntegrationVery simpleStandardModern
Use CaseQuick integration, celebrity voiceProduction appsBest quality, new projects

Getting Started​

  1. Get an API Key

  2. Choose Your Version

    • V3: For new projects, best quality, and smart features
    • V2: For existing integrations using form data
    • V1: For simple integrations or if you need Cee voice

  3. Start Building

    • Follow the documentation for your chosen version
    • Test with the interactive demo
    • Integrate into your application

Common Use Cases​

📚 E-Learning & Education​

Convert text lessons into audio for better learning experiences.

  • Recommended: V3 for best speech quality and smart text handling

🤖 Chatbots & Virtual Assistants​

Add voice to your Thai chatbot or AI assistant.

  • Recommended: V3 for natural conversations and automatic language handling

📻 Content Creation​

Generate voiceovers for videos, podcasts, or announcements.

  • Recommended: V1 (Cee) for celebrity voice, V3 for general content

♿ Accessibility​

Make content accessible to visually impaired users.

  • Recommended: V3 for clarity and naturalness

📱 Mobile Apps​

Add text-to-speech to your iOS/Android applications.

  • Recommended: V3 for best user experience

Core Features​

All versions include:

✅ Natural speech synthesis
✅ Thai-English mixed text support
✅ Fast processing (< 1 second)
✅ Number and date formatting
✅ Emoji support
✅ Currency value conversion
✅ GDPR & PDPA compliant
✅ No data retention

Pricing​

All versions use the same pricing model:

  • Cost: 1 IC per 400 characters
  • Free Trial: 50 IC credits for new users
  • Volume Discounts: Available for large-scale usage

View Pricing Details →

Need Help?​

API Endpoints Summary​

Version 3 (POST JSON) - Recommended​

POST https://api.iapp.co.th/v3/store/audio/tts/generate
Content-Type: application/json
Body: {"text": "Your text here"}

Version 2 (POST Form Data)​

POST https://api.iapp.co.th/v3/store/speech/text-to-speech/kaitom

Version 1 (GET)​

GET https://api.iapp.co.th/v3/store/speech/text-to-speech/kaitom/v1
GET https://api.iapp.co.th/v3/store/speech/text-to-speech/cee