Soprano: Instant, Ultra-Realistic Text-to-Speech

The ultimate training toolkit for finetuning diffusion models

VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

An easy-to-use Mod Organizer 2 installer for Linux

Free, open-source VHS effect. Standalone application + plugin (After Effects, Premiere, and OpenFX).

Redis re-implemented with SQL

Prefab to make players follow moving colliders correctly. Effectively parents players to objects.

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

MFCC-based LipSync plug-in for Unity using Job System and Burst Compiler

Using @131 's h264-live-player but struggling with multiple watchers? Here I present a simple server to solve that for you.

Easily train a good VC model with voice data <= 10 mins!

Check whether a lat/lon point is on land for any point on earth