Text to SpeechMade Intelligent
High-performance TTS API with intelligent caching, multi-provider support, and embeddable audio players. Generate once, serve millions.
Everything You Need
A complete text-to-speech solution with features designed for scale, performance, and developer happiness.
Lightning Fast
Fast response times for cached content. Generate once, serve instantly to millions.
Cost Efficient
Reduce TTS costs through intelligent caching and provider optimization.
Multi-Provider
Seamlessly switch between OpenAI, Cartesia, Coqui, and more. No vendor lock-in.
Scalable Storage
Multi-tier caching with file cache, Redis, and S3 storage options.
Developer Friendly
Simple REST API with JavaScript/TypeScript SDK. Get started in minutes.
Enterprise Security
Encryption at rest and in transit. Your data is safe.
Customizable
Fine-tune voice parameters, caching rules, and routing logic to your needs.
Premium Quality
Access the best voices from each provider. Consistent quality guaranteed.
Privacy Focused
Privacy by design with strong data protection practices.
Best-in-Class Providers
Access the world's best TTS providers through a single API. Switch providers instantly or let our smart routing choose for you.
OpenAI
Industry-leading voices with natural intonation
Popular Voices:
Cartesia
Ultra-fast streaming with low latency
Popular Voices:
Coqui
Open-source with voice cloning capabilities
Popular Voices:
Piper
Fast local TTS for privacy-sensitive content
Popular Voices:
Azure
Enterprise-grade with extensive language support
Popular Voices:
And more providers coming soon...
Embeddable Audio Players
Beautiful, customizable audio players that work anywhere. Just like SoundCloud, but for your generated speech.
Live Preview
Customization Options
Minimal Player
A simple, clean audio player for basic needs
<iframe
src="https://www.tts.supernal.ai/embed/player?hash=abc123"
width="100%"
height="80"
frameborder="0"
></iframe>Advanced Embedding Options
- • Custom colors and themes
- • Responsive sizing
- • JavaScript API for player control
- • Analytics and playback tracking
- • Custom branding options
Simple, Powerful API
Get started in minutes with our RESTful API. Generate speech with a single request, or use our JavaScript/TypeScript SDK.
Quick Start
- 1Sign up and get your API key
- 2Make your first API request
- 3Receive audio URL instantly
API Features
- RESTful API design
- Batch processing support
- Webhook notifications
- Rate limiting protection
- Detailed error messages
SDK Available
Official SDK:
curl -X POST https://api.supernal-tts.ai/v1/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Hello, this is a test of the Supernal TTS API.",
"options": {
"voice": "nova",
"provider": "openai",
"format": "mp3"
}
}'Response:
{
"hash": "a1b2c3d4e5f6g7h8",
"audio_url": "https://api.supernal-tts.ai/audio/a1b2c3d4e5f6g7h8",
"cached": true,
"metadata": {
"duration": 2.34,
"size": 37632,
"provider": "openai",
"voice": "nova",
"generated_at": "2024-01-15T10:30:00Z"
}
}Test the API directly in your browser. No setup required.
Simple, Transparent Pricing
Start free and scale as you grow. No hidden fees, no surprises. Just powerful TTS that works.
Starter
Perfect for trying out our service
- 1,000 characters/month
- 2 TTS providers
- Basic caching
- Community support
- API access
- Custom voices
- Priority support
- SLA guarantee
Pro
For growing applications
- 100,000 characters/month
- All TTS providers
- Advanced caching
- Email support
- Batch processing
- Custom voices
- Analytics dashboard
- High uptime target
Enterprise
For large-scale deployments
- Unlimited characters
- All providers + custom
- Global CDN caching
- Dedicated support
- On-premise option
- Voice cloning
- Custom SLA
- White-label option
All plans include core features like intelligent caching, multiple formats, and API access.