We’re excited to introduce the most expressive and capable open-source lip-syncing software available today. MemoAvatar brings characters to life with impressive realism, handling several minutes of text at a time while maintaining smooth, natural speech animation.
When paired with models like Flux for image creation and Zonos for text-to-speech, you get a complete animation workflow suitable for content creators, animators, VTubers, and AI storytellers.
Originally designed for WSL command-line execution, this new Windows GUI makes the experience simple and accessible—exclusive to Get Going Fast members.
Important: This installation requires CUDA 12 for proper performance.