Pass IndexThe State of AISign in

HiggsAudioV2.5

HiggsAudioV2.5 is a high-quality neural text-to-speech (TTS) model designed for natural-sounding voice generation across a wide range of use cases.

text → audio · made by Boson AI

$0.00002per character
DeepInfra

Sold by 1 way

SellerLaneRate
DeepInfra aggregatorstandard$20per million charactersapi.deepinfra.com · read 2026-08-25

About

HiggsAudioV2.5 — an audio model from Boson AI, sold by one company from $20 per million characters.

It takes text and returns audio. The catalogue files it under speak. Only DeepInfra sells it, at $20 per million characters.

Every current figure

Maker
Boson AI
Register
model
Takes
text
Returns
audio
Sellers
1
Maker's own price
not read
Price
$20 per million characters — DeepInfra

Known as 1 name

bosonai/HiggsAudioV2.5