v1.0.0 - OpenAI-compatible TTS server with XTTS-v2

Features:
- POST /v1/audio/speech (OpenAI-compatible)
- GET /v1/models, /v1/voices, /health
- Authorization via API_KEY env (optional)
- model=text-to-speech required
- Default voice embedded in image
- GPU auto-detection (CUDA)
- LiteLLM proxy compatible
- Port 8000