Definition
Text-to-video is an AI technique that turns a written description into a moving video clip — no camera, footage, or actors. You describe the shot (subject, action, camera move, mood) and the model renders it frame by frame. Quality, length, and control vary by model.
How it works in Ekly
Ekly runs many text-to-video models — Veo, Kling, Seedance, and more — under one plan, so you can pick the best one per shot and drop the result straight onto a timeline.
One plan. Every model.
Start free — no card. Generate, then finish on the same timeline.