vits-ljs
VITS is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence.
text → audio · made by Kakao Enterprise
Sold by
Nobody in the catalogue publishes a price for this yet.
About
vits-ljs — an audio model from Kakao Enterprise.
It takes text and returns audio. It was published in August 2023. The catalogue files it under speak. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Kakao Enterprise
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- August 2023
- Parameters
- 36 million · read from its own weights
- Licence
- mit
Known as 1 name
kakao-enterprise/vits-ljs