Pass IndexThe State of AISign in

MOSS-TTS

When a single piece of audio needs to sound like a real person, pronounce every word accurately, switch speaking styles across content, remain stable over tens of minutes, and support dialogue, role‑play, and real‑time interaction, a single TTS model is often not enough.

text → audio · made by OpenMOSS-Team

Sold by

Nobody in the catalogue publishes a price for this yet.

About

MOSS-TTS — an audio model from OpenMOSS-Team.

It takes text and returns audio. It was published in February 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
OpenMOSS-Team
Register
model
Takes
text
Returns
audio
Published
February 2026
Parameters
8.5 billion · read from its own weights
Licence
apache-2.0

Known as 1 name

OpenMOSS-Team/MOSS-TTS