Metadata-Version: 2.1
Name: moonshine-lite
Version: 0.0.3
Summary: Lite wrapper for the useful-moonshine speech to text models
Author-email: Yaser Martinez Palenzuela <yaser.martinez@gmail.com>
Project-URL: Homepage, https://elyase.github.io/moonshine-lite/
Project-URL: Repository, https://github.com/elyase/moonshine-lite
Project-URL: Documentation, https://elyase.github.io/moonshine-lite/
Keywords: python
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: <4.0,>=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: huggingface-hub>=0.26.2
Requires-Dist: onnxruntime>=1.20.0
Requires-Dist: pynput>=1.7.7
Requires-Dist: silero-vad>=5.1.2
Requires-Dist: sounddevice>=0.5.1
Requires-Dist: tokenizers>=0.20.3

# 🎙️ Moonshine Lite

[![Release](https://img.shields.io/github/v/release/elyase/moonshine-lite)](https://img.shields.io/github/v/release/elyase/moonshine-lite)
[![Build status](https://img.shields.io/github/actions/workflow/status/elyase/moonshine-lite/main.yml?branch=main)](https://github.com/elyase/moonshine-lite/actions/workflows/main.yml?query=branch%3Amain)
[![License](https://img.shields.io/github/license/elyase/moonshine-lite)](https://img.shields.io/github/license/elyase/moonshine-lite)

> 🚀 A lightweight Python wrapper for the [moonshine](https://github.com/usefulsensors/moonshine/) speech-to-text models with real-time transcription capabilities

## ✨ Features

- ⚡ Small and fast (60MB model size)
- 🎤 Real-time transcription from microphone
- ⌨️ Simulated keyboard typing for app integration
- 📝 Support for WAV file transcription
- 🎯 Simple API (`listen` and `transcribe` methods)

## 🚀 Quick Start

### Installation

```bash
pip install moonshine-lite
```

### Basic Usage

```python
from moonshine_lite import Moonshine

moonshine = Moonshine()

# Transcribe a WAV file
text = moonshine.transcribe("audio.wav")
print(text)

# Start live transcription (text will be typed in the current application)
# you need to press and hold the activation key (Cmd by default) to start listening
moonshine.listen()
```

### 💻 CLI

```bash
# Transcribe a WAV file
moonshine transcribe "audio.wav"

# Start live transcription (text will be typed in the current application)
# you need to press and hold the activation key (Cmd by default) to start listening
moonshine listen

# Use tiny model
moonshine --model moonshine/tiny listen
```

## 🙏 Credits

- [Useful Sensors' Moonshine models](https://github.com/usefulsensors/moonshine/)
- [Silero VAD](https://github.com/snakers4/silero-vad) for voice activity detection

## 📚 Documentation

No need :-D

---

Made with ❤️ by [Yaser Martinez Palenzuela](https://github.com/elyase)
