Picovoice/leopard
An on-device speech-to-text engine that runs deep learning models locally for automatic speech recognition.
Not currently ranked — collecting fresh signals.
star history
Leopard is Picovoice’s speech-to-text engine that processes audio locally without requiring cloud connectivity. It uses deep learning models optimized for edge deployment to convert spoken language into written text. The engine supports multiple platforms including Python, Node.js, React, React Native, web browsers, Android, iOS, Flutter, and .NET.
Frequently asked
- What is Picovoice/leopard?
- An on-device speech-to-text engine that runs deep learning models locally for automatic speech recognition.
- Is leopard open source?
- Yes — Picovoice/leopard is open source, released under the Apache-2.0 license.
- What language is leopard written in?
- Picovoice/leopard is primarily written in Python.
- How popular is leopard?
- Picovoice/leopard has 482 stars on GitHub.
- Where can I find leopard?
- Picovoice/leopard is on GitHub at https://github.com/Picovoice/leopard.