Initial commit

This commit is contained in:
elmadani 2026-02-25 00:53:21 +00:00
commit a71c349418

43
README.md Normal file
View File

@ -0,0 +1,43 @@
# IX Voice
*Part of the Inference-X Ecosystem*
[![License: BSL-1.1](https://img.shields.io/badge/License-BSL_1.1-orange.svg)](LICENSE)
[![Part of IX](https://img.shields.io/badge/Inference--X-ecosystem-copper.svg)](https://inference-x.com)
**Neural voice synthesis. Clone, create, share voice models.**
Same philosophy as IX Engine: **local, private, yours.**
## What it does
- Analyze voice characteristics from a WAV sample (Z-equation based)
- Synthesize speech with cloned vocal profile
- Zero cloud dependency — runs entirely on your hardware
- Export and share voice models with the community
## Quick Start
```bash
pip install fastapi uvicorn numpy
python ix_voice.py
# → API running at http://localhost:8000
```
## API Endpoints
```
POST /synthesize — Clone voice + synthesize speech from WAV + text
GET /health — System status
```
## Philosophy
Your voice is yours. No cloud upload. No subscription.
Signal processing on your own silicon, powered by the Z-equation.
```
Z = dI/d(log s) * exp(i*theta)
```
Built in Morocco for the world. 🇲🇦
## License
[Business Source License 1.1](LICENSE) — Free for personal/research/non-commercial use.
Commercial production use above $1M revenue requires a license.
**Author:** Salka Elmadani · Elmadani.SALKA@proton.me