Metadata-Version: 2.4
Name: suzune-mini
Version: 0.1.0
Summary: Ultra-Lightweight On-Device Flow-Matching Neural Speech Engine by Sorika Labs
Author-email: Sorika Labs <contact@sorikalabs.com>
Project-URL: Homepage, https://huggingface.co/sorika-labs/suzune-s1-mini
Project-URL: Repository, https://huggingface.co/sorika-labs/suzune-s1-mini
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: ptts>=0.1.0
Requires-Dist: soundfile>=0.12.0
Requires-Dist: huggingface_hub>=0.20.0

# 🌸 Suzune Mini (40M On-Device Causal Flow TTS)

[![PyPI](https://img.shields.io/badge/pypi-suzune--mini-blue.svg)](https://pypi.org/project/suzune-mini/)
[![Hugging Face](https://img.shields.io/badge/HF%20Model-sorika--labs%2Fsuzune--s1--mini-yellow)](https://huggingface.co/sorika-labs/suzune-s1-mini)
[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](LICENSE)

**Suzune Mini** is an ultra-compact, 40-million parameter on-device Text-to-Speech (TTS) foundation model engineered by **Sorika Labs**. 

Powered by causal flow-matching and neural latent acoustic decoding, Suzune Mini delivers first-audio latency under **10ms** directly on laptop CPUs, mobile devices, edge compute, and Apple Silicon, with zero network round-trip.

---

## 🏛️ Base Model & Lineage

> **Lineage & Attribution**:
> Suzune S1 Mini is developed and released by **Sorika Labs**. Its underlying causal flow-matching acoustic architecture is adapted and fine-tuned from the open-source [`gradium/phonon-31m-en`](https://huggingface.co/gradium/phonon-31m-en) foundation (released under Apache 2.0).
>
> **Sorika Labs Enhancements & Customizations**:
> 1. **Calibrated High-Fidelity Voice Manifolds**: Built-in voice profiles including `Zoey`, `Harper`, `Easton`, `Juniper`, `Austin`, and `Aria`.
> 2. **Causal Acoustic Optimization**: Streamlined latent flow generation for sub-10ms real-time conversational agents.
> 3. **Standalone `suzune-mini` SDK**: Clean, high-level Python API with zero complex boilerplate.

---

## 🚀 Quick Install

```bash
pip install suzune-mini
```

---

## 🎙️ Python Quickstart

Synthesize speech in 3 lines of code:

```python
import suzune_mini

# Load Suzune Mini engine (default voice: 'Zoey')
tts = suzune_mini.load(voice="Zoey")

# Generate speech
audio, sr = tts.speak(
    "Hello! Suzune Mini is running 100% on device with sub-10ms latency.",
    output="speech.wav"
)
```

---

## 🎭 Available Built-in Voices

| Voice Name | Gender | Characteristics / Style |
| :--- | :--- | :--- |
| **`Zoey`** | Female | Natural, articulate, modern conversational (Default) |
| **`Harper`** | Female | Expressive, warm, narrative |
| **`Easton`** | Male | Clear, confident, balanced |
| **`Juniper`** | Female | Soft, friendly, customer-facing |
| **`Austin`** | Male | Deep, energetic, professional |

---

## 💻 Terminal Command Line (CLI)

```bash
suzune-mini "Hello from Sorika Labs on-device AI!" --voice Zoey --output output.wav
```

---

## 📜 License & Citation

Licensed under the **Apache 2.0 License**.

```bibtex
@misc{sorika2026suzunemini,
  author = {Sorika Labs},
  title = {Suzune S1 Mini: Ultra-Lightweight On-Device Flow-Matching Speech Foundation Model},
  year = {2026},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  howpublished = {https://huggingface.co/sorika-labs/suzune-s1-mini}
}
```
