🎙️ Moonshine Lite

🚀 A lightweight Python wrapper for the 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

pip install moonshine-lite

Basic Usage

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

# 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
• Silero VAD for voice activity detection

📚 Documentation

No need :-D

Made with ❤️ by Yaser Martinez Palenzuela