hush
The first open-source speech enhancement model built specifically for Voice AI — with real-time background speaker suppression.
audio → audio · made by weya-ai
Sold by
Nobody in the catalogue publishes a price for this yet.
About
hush — an audio model from weya-ai.
It takes audio and returns audio. It was published in March 2026. The catalogue files it under speak. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- weya-ai
- Register
- model
- Takes
- audio
- Returns
- audio
- Published
- March 2026
- Licence
- apache-2.0
Known as 1 name
weya-ai/hush