ZipVoice
This model consists of checkpoints for two fast and high-quality non-autoregressive zero-shot text-to-speech models:.
text → audio · made by k2-fsa
Sold by
Nobody in the catalogue publishes a price for this yet.
About
ZipVoice — an audio model from k2-fsa.
It takes text and returns audio. It was published in June 2025. The catalogue files it under speak.
Every current figure
- Maker
- k2-fsa
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- June 2025
Known as 1 name
k2-fsa/ZipVoice