An AI-powered lip sync tool that automatically generates facial animations from audio files within Blender. It processes speech to detect phonemes and translates them into appropriate mouth movements using either shape keys or armature-based action rigs.

The system includes tools for custom shape key mapping and can automatically generate required shape keys if they are missing from a character mesh. A batch processing mode is available for handling scenes with multiple characters and distinct dialogue tracks simultaneously. All speech processing occurs locally after an initial download of the required AI models.