NovaSR
This is the model for NovaSR, a tiny 50kB audio upsampling model that upscales muffled 16khz audio into clear and crisp 48khz audio at speeds from 100-3500x realtime.
audio → audio · made by YatharthS
Sold by
Nobody in the catalogue publishes a price for this yet.
About
NovaSR — an audio model from YatharthS.
It takes audio and returns audio. It was published in January 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
- YatharthS
- Register
- model
- Takes
- audio
- Returns
- audio
- Published
- January 2026
- Licence
- apache-2.0
Known as 1 name
YatharthS/NovaSR