Woof
Underdog released Woof, a 31.7MB text-to-speech model that runs in a browser, and showed it in a browser game. The model can also generate music.
Woof is a 31 million parameter voice model small enough to run offline on most devices. Underdog showed it in a browser game where typed text is spoken back and a tuner generates music. It follows Bark, a 167MB speech-to-text model the company released weeks earlier.
- Date
- Thursday 5 November 2026
- Lab
- Underdog
- Kind
- open-weights
- Access
- open weights
Figures
| Measure | Value | Measured by |
|---|---|---|
| Model size | 31.7 MB about 31 million parameters | company |
Date taken from Underdog's X post of 2026-11-05 quoted by TechCrunch. Open download is stated by TechCrunch and the license was not read.
Sources
This record was checked against its sources on 6 November 2026. How we check