My work with ElevenLabs for THE GALLERY / SIMUL ACTIONS, exploring how Voice Design, text-to-speech tags, and phonetic rewriting can transform a synthetic voice into a theatrical performer. Starting from a Latin text for a tragic coryphaeus and chorus, I describe the process of shaping pronunciation, rhythm, emotional tone, and vocal presence through a form of micro vocal direction.

A practical alternative to Blender for AI filmmaking: how to reconstruct navigable 3D scenes from images, panoramas, and video for spatially coherent cinematic shots.

One of the most important things in my AI-generated performances is spatial coherence. Not just making a beautiful image, but building a reusable environment that can hold multiple shots.