Voice acting is an integral component of modern video games, effectively providing much realism and immersiveness. This comes at a cost, however, as tinkerers (modders) don’t have access to the original professional voice actors used in the games’ creation processes. This usually means user generated content suffers from a lack of voiced characters, or often sub-par quality of voice recordings where recording equipment is not very good.

This is a companion post for the v1.0 release of xVASynth, a tool I’ve been working on since 2018, which aims to tackle this problem using established neural speech synthesis techniques. I’ll go…

Dan Ruta

AI PhD student @ UoSurrey & Adobe | Software developer https://danruta.co.uk @Dan_Ruta

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store