Snowboy is a deep neural network-based wake word detection engine that runs entirely on-device, processing live audio to recognize a spoken trigger phrase without sending any data to the cloud. The project provides both pre-trained universal models for common wake words like "Alexa" or "Snowboy" and the ability to detect a custom wake word defined by the user.
The engine is designed to be lightweight enough for embedded devices, using less than 10% CPU on a single-core 700MHz ARM processor such as a Raspberry Pi. Users can train a personalized wake-word model by submitting voice samples through a REST API and receiving a trained model file, or tune the sensitivity and audio gain settings on the ready-made universal models.
The detection engine is accessible through language bindings for Python, Go, Perl, Java, Node.js, iOS, and C/C++, enabling integration into a wide range of applications. The project includes documentation and installation instructions for building and using the library across these supported platforms.
