Pass IndexThe State of AISign in

higgs-tts-3-4b

Higgs TTS 3 is built for voice chat: it speaks, not just reads.

text → audio · made by Boson AI

Sold by

Nobody in the catalogue publishes a price for this yet.

About

higgs-tts-3-4b — an audio model from Boson AI.

It takes text and returns audio. It was published in June 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
Boson AI
Register
model
Takes
text
Returns
audio
Published
June 2026
Parameters
4.7 billion · read from its own weights
Licence
other

Known as 1 name

bosonai/higgs-tts-3-4b