arcosoph/nanowakeword

A lightweight, open-source, and intelligent wake word detection engine. Train custom, high-accuracy models with minimal effort.

55
/ 100
Established

This project helps anyone who wants to build a custom voice assistant or create voice-activated controls for devices. You provide audio recordings of the specific 'wake word' or phrase you want your system to respond to. The project then generates a highly accurate, custom wake word model that can be deployed on a variety of devices. It's ideal for product managers, embedded systems engineers, or entrepreneurs developing voice-controlled products.

Available on PyPI.

Use this if you need to create a reliable and custom wake word detection system for a specific phrase, especially for embedded devices or noisy environments.

Not ideal if you're looking for a general-purpose speech-to-text solution or a pre-trained model for common wake words like "Hey Google" or "Alexa."

voice-assistants embedded-systems product-development audio-processing IoT
Maintenance 10 / 25
Adoption 8 / 25
Maturity 24 / 25
Community 13 / 25

How are scores calculated?

Stars

48

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2026

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/arcosoph/nanowakeword"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.