Caira’s AI mirrorless camera is getting ‘Nano Banana for video editing’ — but it only works on footage you’ve actually shot
Caira’s new generative video tools can transform footage using natural-language instructions while keeping the original recording at the heart of every edit.
Caira has introduced a new Generative Video Editing feature powered by Google's Gemini Omni 1.1 Flash and Runway's Aleph 2.0. This feature allows users to relight, reframe, extend and add simulated camera movements to footage captured using the Caira AI camera. The edits are made using natural language instructions through the Caira app and saved separately as AI-generated results.
Camera Intelligence, the AI camera startup behind Caira, claims to be the first company to integrate video generation models into a mirrorless camera system. The feature will initially be available for Caira customers in a private beta and later integrated into the paid Caira Studio software package in Autumn 2026, though no pricing has been announced yet.
The edit must start with footage shot on the Caira camera; AI-generated results are not standalone. With the new feature, Camera Intelligence aims to bring generative AI as close as possible to the act of filming, keeping the creative process rooted in photography.
Written by urgent.news from TechRadar's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
