evancohen/sonus
:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection
Leverages Snowboy for local hotword detection without cloud dependency, then streams only triggered audio to cloud speech providers like Google Cloud Speech for recognition. Supports multiple customizable hotwords per instance and streams results in real-time, making it suitable for voice-driven IoT and home automation projects. Requires SoX for audio capture and currently targets Linux and macOS platforms.
636 stars and 116 monthly downloads. No commits in the last 6 months. Available on npm.
Stars
636
Forks
77
Language
JavaScript
License
MIT
Category
Last pushed
Jul 02, 2024
Monthly downloads
116
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.
Related tools
TalAter/annyang
💬 Speech recognition for your site
Picovoice/web-voice-processor
A library for real-time voice processing in web browsers
EddyVerbruggen/nativescript-speech-recognition
:speech_balloon: Speech to text, using the awesome engines readily available on the device.
sdkcarlos/artyom.js
A voice control - voice commands - speech recognition and speech synthesis javascript library....
antirek/voicer
AGI-server voice recognizer for #Asterisk