VoxCPM2
VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.
text → audio · made by OpenBMB
Sold by
Nobody in the catalogue publishes a price for this yet.
About
VoxCPM2 — an audio model from OpenBMB.
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
- OpenBMB
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- April 2026
- Parameters
- 2.3 billion · read from its own weights
- Licence
- apache-2.0
Known as 1 name
openbmb/VoxCPM2