๐๏ธ Supernal TTS
High-performance Text-to-Speech API with multi-provider support, intelligent caching, and real-time audio generation.
:::tip Development Status Supernal TTS is currently in active development. While functional, some features may be incomplete or subject to change. We appreciate your patience as we work to deliver the best TTS experience possible! :::
โจ Featuresโ
- ๐ Multi-Provider Support - OpenAI, Cartesia, Azure, and Mock providers
- โก Fast Performance - High-performance audio generation with intelligent caching
- ๐พ Intelligent Caching - Automatic content-based caching
- ๐ Production Ready - Authentication, rate limiting, security headers
- ๐ฏ Easy Integration - REST API, JavaScript SDK, and web widget
- ๐ฐ Cost Optimization - Provider comparison and cost estimation
๐ Add Voice to Your Website (Choose Your Way)โ
๐ Gtag-Style (Recommended)โ
Like Google Analytics - Zero config!
<script src="https://unpkg.com/@supernal/tts-widget@1/dist/widget.js"></script>
<script>
window.SupernalTTS.init({ apiKey: 'YOUR_KEY' });
</script>
<div class="supernal-tts-widget" data-text="Content">
Content
</div>
โ No bundler โ No npm โ Works everywhere
๐ฆ NPM Packageโ
For build tool users
npm install @supernal/tts-widget
import { SupernalTTS } from '@supernal/tts-widget';
SupernalTTS.init({ apiKey: 'YOUR_KEY' });
โ Version locked โ TypeScript support โ Works offline
โ๏ธ React Componentโ
For React purists
import { TTSInitializer } from '@supernal/tts-widget/react';
<TTSInitializer apiKey="YOUR_KEY" />
โ Props-based config โ Type-safe โ React-friendly
โ Complete Installation Guide โ
๐ Get Your Free API Keyโ
- Visit www.tts.supernal.ai
- Sign up (free!)
- Copy your API key
- Start adding voice to your site!
๐ ๏ธ For Developers: Self-Hosted APIโ
1. Install and Runโ
# Clone the repository
git clone https://github.com/supernalintelligence/supernal-nova.git
cd supernal-nova/families/supernal-tts
# Install dependencies
npm install
# Start the server (uses mock provider by default)
npm run dev
The API will be available at http://localhost:3030
2. Test with Mock Providerโ
curl -X POST https://tts.supernal.ai/api/v1/generate \
-H "Content-Type: application/json" \
-d '{
"text": "Hello world!",
"options": {
"provider": "mock"
}
}'
3. Add Real Providersโ
Create a .env file:
# OpenAI (recommended for quality)
OPENAI_API_KEY=sk-...
# Cartesia (recommended for speed)
CARTESIA_API_KEY=...
# Azure (recommended for budget)
AZURE_API_KEY=...
AZURE_REGION=eastus
4. Generate Real Audioโ
curl -X POST https://tts.supernal.ai/api/v1/generate \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome to Supernal TTS!",
"options": {
"provider": "openai",
"voice": "fable"
}
}'
๐ฏ Provider Comparisonโ
| Provider | Performance | Cost/1M chars | Best For | Key Feature |
|---|---|---|---|---|
mock | Development | $0 | Testing | No API key needed |
openai | High | $15-30 | Quality | 6 premium voices |
cartesia | Fast | ~$24 | Real-time | Emotion control |
azure | Good | $0-16 | Budget | 500K free tier |
๐ Next Stepsโ
- ๐ API Reference - Complete API documentation
- โก Quick Reference - Commands and examples
- ๐ Security Guide - Production deployment
- ๐จ Widget Guide - Web integration
- ๐ฆ Examples - Integration examples
๐ฎ Interactive Demoโ
Try the live demo:
- ๐๏ธ Widget Demo - Interactive examples of TTS widgets in action
- ๐ Documentation - Complete integration guide
# Or run comparison tests locally
./demo-scripts/compare-all-providers.sh "Test message"
๐ก Use Casesโ
- Blog Audio - Convert articles to audio
- E-learning - Course narration
- Accessibility - Screen reader enhancement
- Chatbots - Voice responses
- Podcasts - Automated narration
- Games - Character voices
๐ค Supportโ
๐ง Try It Nowโ
:::info Development Preview This TTS widget is currently under active development. Features may not work perfectly and are subject to change. We're working hard to improve the experience! :::
Welcome to Supernal TTS! This is a live demo of our text-to-speech widget using eSpeak (our free, open-source provider). Click the button below to hear this text spoken aloud with real speech synthesis.
Ready to get started? Check out the API Reference or jump to the Quick Reference for common patterns.