Metadata-Version: 2.4
Name: lunavox
Version: 2.1.0
Summary: LunaVox tooling CLI for model setup, conversion, quantization, and build workflows.
Author: LunaVox Contributors
License: MIT
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: typer>=0.12.0
Requires-Dist: rich>=13.7.0
Requires-Dist: huggingface_hub>=0.24.0
Provides-Extra: gui
Requires-Dist: customtkinter>=5.2.0; extra == "gui"
Requires-Dist: pygame>=2.5.0; extra == "gui"
Provides-Extra: convert
Requires-Dist: torch>=2.1; extra == "convert"
Requires-Dist: torchaudio>=2.1; extra == "convert"
Requires-Dist: transformers==4.57.6; extra == "convert"
Requires-Dist: accelerate==1.12.0; extra == "convert"
Requires-Dist: onnx; extra == "convert"
Requires-Dist: onnxruntime; extra == "convert"
Requires-Dist: onnxruntime-tools; extra == "convert"
Requires-Dist: gguf; extra == "convert"
Requires-Dist: numpy; extra == "convert"
Requires-Dist: tqdm; extra == "convert"
Requires-Dist: safetensors; extra == "convert"
Requires-Dist: sentencepiece; extra == "convert"
Requires-Dist: librosa; extra == "convert"
Requires-Dist: scipy; extra == "convert"
Requires-Dist: soundfile; extra == "convert"
Requires-Dist: einops; extra == "convert"
Requires-Dist: onnxscript; extra == "convert"
Provides-Extra: dev
Requires-Dist: pytest>=8.2; extra == "dev"
Requires-Dist: build>=1.2; extra == "dev"
Requires-Dist: twine>=5.1; extra == "dev"
Dynamic: license-file

# 🌌 LunaVox: High-Performance C++ Inference Engine for Qwen3-TTS

![Version](https://img.shields.io/badge/version-2.1.0-blueviolet?style=for-the-badge)
![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20macOS-0078d7?style=for-the-badge&logo=windows&logoColor=white)
![CoreML](https://img.shields.io/badge/iOS-CoreML-000000?style=for-the-badge&logo=apple&logoColor=white)
![C++](https://img.shields.io/badge/C++-17-00599C?style=for-the-badge&logo=c%2B%2B)
[![License](https://img.shields.io/badge/license-MIT-green?style=for-the-badge)](LICENSE)
[![English Docs](https://img.shields.io/badge/docs-English-blue?style=for-the-badge)](docs/en/README.md)
[![中文文档](https://img.shields.io/badge/文档-中文-red?style=for-the-badge)](docs/zh/README_ZH.md)

**LunaVox** is a high-performance C++ inference engine specifically designed for **Qwen3-TTS**. Through streamlined architecture and deep hardware optimization, it provides extreme speech synthesis speed and flexibility.

---

## 🚀 Key Features

- **Lightweight Runtime**: Runs with only ONNX Runtime and a custom Llama inference library, no heavy Python environment required.
- **Native Multi-language Support**: Built-in automatic language detection, supporting **10 languages**.
- **Full Mode Support**: Supports Base synthesis, Voice Cloning, Custom Voice, and Voice Design.
- **Cross-platform Hardware Acceleration**: Deeply integrated with **CUDA, CoreML/Metal, DML, and Vulkan**.

---

## 🛠️ Requirements

- **Python 3.10+**: For model management.
- **CMake 3.16+**: For building the engine.
- **Environment**: Windows 10+, Linux, or macOS 12+.

---

## 📊 Performance

| Configuration | Average RTF | Relative Speedup |
| :--- | :---: | :---: |
| **LunaVox (Full CPU)** | 1.152 | 4.40x |
| **LunaVox (CUDA13)** | 0.254 | 19.94x |
| **LunaVox (Vulkan + DML)**| **0.206** | **24.59x** |

---

## 📦 Quick Start

### Install via PyPI
```powershell
pip install lunavox
```

### Auto Setup
```powershell
lunavox bootstrap
```

---

## 🎙️ Basic Usage

```bash
./build/qwen3-tts-cli.exe `
  -m models/base_small `
  -t "Hi, this is lunavox speaking English." `
  -o output/out.wav
```

---

## 📜 Documentation

- **[English Documentation Hub](docs/en/README.md)**
- **[CLI Reference Guide](docs/en/guide/cli_reference.md)**
- **[Performance Report](docs/en/benchmark/windows_performance.md)**
- **[Runtime Tech Specs](docs/en/technical/runtime_specs.md)**

---

## 🙏 Acknowledgements

- **[Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS)**
- **[onnxruntime](https://github.com/microsoft/onnxruntime)**
- **[llama.cpp](https://github.com/ggml-org/llama.cpp)**
