Describe a scene and AI turns it into a video of 4 to 15 seconds — no photo needed. Pick from 16 current-generation video engines, choose landscape, vertical or square, and hit Generate.
No — text to video creates the scene from your words alone. To animate a photo you already have, use photo to video.
Yes — engines marked "with sound" generate native audio (ambient sound, effects, even speech); Kling 2.6 lets you toggle sound on or off.
250 to 1,300 credits for a standard 5-second clip depending on the engine, scaling linearly with duration — the exact cost is shown on the Generate button. New accounts get 750 free credits; see plans and pricing.