The leaderboard scores how human a model reads. It says nothing about how a model
sounds — that is a different piece of software entirely, and choosing it badly
is where most voice projects go wrong. Here is every text-to-speech system that matters,
on the axes that actually decide a project.
Surveyed, not benchmarked. Nothing on this page was measured by
OpenGauntlet.
//
Every system, compared
Filter by kind or by what a system can actually do, pick the columns you care about,
search any field, click a heading to sort. Every row carries the one thing a buyer
would otherwise find out too late.
Loading…
commercial-safe weights permissive, with a catchnot usable commercially proprietary service discontinued
//
Claims this corrects
Each of these is repeated widely, and each is wrong.
//
What we couldn't establish
A comparison that hides its gaps is less useful than one that names them.