Intelligent multi-cloud orchestration platform for text-to-speech services with automatic routing and enterprise-grade management.
Platform | Status | Features |
---|---|---|
Azure Cognitive | ✅ Live | Neural Voices, SSML, Real-time |
Edge-TTS | ✅ Live | Free Tier, 20+ Voices |
AWS Polly | 🚧 Beta | Neural & Standard Voices |
Google Cloud | 🚧 Planned | WaveNet Voices |
- Smart Routing: Auto-select optimal TTS engine based on cost/language
- Real-time Streaming: Low-latency audio delivery (MP3/WAV)
- Enterprise Ready:
- Full request tracing (X-Request-ID)
- Structured logging with request context
- Automated temp file cleanup
graph TD
WebApp -->|API Call| TTS-Gateway
TTS-Gateway -->|Load Balance| Azure-TTS
TTS-Gateway -->|Fallback| Edge-TTS
TTS-Gateway -->|Premium| AWS-Polly
TTS-Gateway --> Cache[(Redis)]
# Install dependencies
pip install -r requirements.txt
# Configure environment
cp .env.example .env
# Start service (dev)
uvicorn backend.main:app --reload
cd frontend
npm install
npm start
startLine: 9
endLine: 18
Request Example:
curl -X POST "https://YOUR_DOMAIN/api/generate" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome to TTS Gateway",
"voice": "en-US-JennyNeural",
"azure_key": "YOUR_KEY",
"azure_region": "eastus"
}'
- AWS Polly integration
- Audio post-processing pipeline
- Rate limiting
- Google Cloud TTS support
- Multi-tenant architecture
- Voice cloning API
startLine: 38
endLine: 45
Set environment variables:
startLine: 1
endLine: 7
See CONTRIBUTING.md for development setup and guidelines.