Metadata-Version: 2.4
Name: voxcore-local
Version: 0.1.0
Summary: Local voice assistant pipeline — STT → LLM → TTS, 100% offline
Author-email: Ali <ali@voxcore.dev>
License: MIT
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: faster-whisper>=1.0.0
Requires-Dist: openai>=1.0.0
Requires-Dist: pydub>=0.25.0
Requires-Dist: requests>=2.31.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: click>=8.1.0
Requires-Dist: sounddevice>=0.4.6
Requires-Dist: soundfile>=0.12.0
Requires-Dist: numpy>=1.24.0
Provides-Extra: dev
Requires-Dist: pytest>=7.4.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Dynamic: license-file

# VoxCore

Local voice assistant pipeline — STT → LLM → TTS, 100% offline.

**Stack** : faster-whisper + Qwen3.6 + Voxtral (ou Supertonic/Piper)

**Installation** :
```bash
pip install voxcore
voxcore --config config.yaml
```

**Usage** :
```bash
# Microphone → réponse vocale
voxcore live

# Audio file → texte
voxcore stt input.wav

# Texte → audio
voxcore tts "Hello world" -o output.mp3
```

**Config** : `config.yaml` dans le dossier courant ou `~/.config/voxcore/config.yaml`

## Architecture
- `stt/` — Speech-to-Text (faster-whisper)
- `llm/` — Local LLM (llama.cpp, vLLM, LM Studio)
- `tts/` — Text-to-Speech (Voxtral, Piper, Supertonic)
- `pipeline/` — Orchestration complète

## Requirements
- Python 3.10+
- GPU NVIDIA recommandé (CUDA 12+)
- RAM : 16GB minimum

## License
MIT
