Pass IndexThe State of AISign in

MisoTTS

Miso TTS 8B is a text-to-speech model based on the Sesame CSM architecture.

text → audio · made by Miso Labs

Sold by

Nobody in the catalogue publishes a price for this yet.

About

MisoTTS — an audio model from Miso Labs.

It takes text and returns audio. It was published in May 2026. The catalogue files it under speak. Its weights are published under the other licence, which attaches conditions the plain open licences do not.

Every current figure

Maker
Miso Labs
Register
model
Takes
text
Returns
audio
Published
May 2026
Parameters
8.2 billion · read from its own weights
Licence
other

Known as 1 name

MisoLabs/MisoTTS