AI Agent Skills

Genblaze is an open source Python SDK for orchestrating generative AI media pipelines across video, audio, and image providers with built in provenance for every output.

A TTS model capable of generating ultra-realistic dialogue in one pass.

A voice chat app

TTS model capable of streaming conversational audio in realtime.

AI Agent Skill for Prompting Video Models

Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)