Research

Introducing three new languages: Hungarian, Vietnamese and Norwegian
Expand your audience and create high quality audio in 32 languages

Expand your audience and create high quality audio in 32 languages

High quality, low latency text to speech in 32 languages

Our fastest model now has improved numbers pronunciation

The advancement will allow media companies, game developers, publishers and independent creators across the world to dramatically improve the accessibility of their content.

Our current deep learning approach leverages more data, more computational power, and novel techniques to deliver our most advanced speech synthesis model

We’re deploying our own generative model which lets users design entirely new synthetic voices