evancohen/sonus

:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection

54
/ 100
Established

This tool helps developers integrate voice commands into their software or hardware projects. It takes audio input, listens for a specific customizable "hotword" offline, and then streams subsequent speech to a cloud service for real-time transcription. The output is text that can be used to control applications or devices, making it ideal for engineers building voice-activated systems.

636 stars. No commits in the last 6 months. Available on npm.

Use this if you are a developer creating a voice user interface for a product or system, similar to smart home assistants, and need robust speech-to-text capabilities with offline hotword detection.

Not ideal if you need an out-of-the-box voice assistant application rather than a component to build one.

voice-control embedded-systems IoT-development home-automation VUI-design
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

636

Forks

77

Language

JavaScript

License

MIT

Last pushed

Jul 02, 2024

Commits (30d)

0

Dependencies

3

Get this data via API

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

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