real-time AI

Fal released H3 Max Live, a post-trained and inference-optimized version of Minimax's H3 video model that Fal claims runs up to 35x faster than the official endpoint. The model generates video faster than it can be watched, enabling an infinite, chat-directed live video stream.

Researchers have introduced LPM 1.0, an AI model that generates real-time video of a speaking, listening, or singing character from a single image, with lip-synced speech and facial expressions stable for up to 45 minutes. The system integrates directly with voice AI models like ChatGPT but remains a research project with no planned public release.