Sign In
V

VITS

Foundational end-to-end open architecture that influenced many modern TTS models.

AIopen source

Setup complexity

hard

Platforms

Windows, macOS, Linux, Web

Current version

Latest activity signal

Not specified

Overview

VITS is a seminal end-to-end text-to-speech architecture combining variational inference with adversarial training.

Integrations

Research code

Get the weekly tool roundup

Keep up with tools like VITS. One concise email per week.