omnivoice-singing
Original OmniVoice capabilities (multilingual zero-shot TTS, voice cloning, voice design, 600+ languages) are preserved — the base speech head was protected during finetuning with a continuity mix of plain speech and singing.
text → audio · made by ModelsLab
Sold by
Nobody in the catalogue publishes a price for this yet.
About
omnivoice-singing — an audio model from ModelsLab.
It takes text and returns audio. It was published in April 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
- ModelsLab
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- April 2026
- Parameters
- 613 million · read from its own weights
- Licence
- apache-2.0
Known as 1 name
ModelsLab/omnivoice-singing