Your director studio · text or image to video · shot timeline
Video Prompt Generator
Choose text to video or image to video, plan your shots with real camera moves, add dialogue and sound, and watch the preview play. Copy a prompt for Veo, Kling, Sora, Seedance, Hailuo or Grok.
Start from a templateShots, moves and sound included
3Your idea
4 Shots and camera
Tap a shot to edit it. Add shots to tell a story.
5 Direct the scene
Options change with your mode, video type and AI model. ✨ Auto picks for you and keeps up as you change things.
How the AI Video Studio works
Choose how to start: text to video creates the whole scene from your words. Image to video brings your own photo, product or artwork to life.
Plan your shots: add shots with a size, camera move, length and action. The live preview plays them back so you can feel the edit.
Add dialogue and sound, then copy: voices, background sound, effects and music, formatted for Veo, Kling, Sora, Seedance, Hailuo or Grok.
Frequently asked questions
Text to video or image to video: which should I use?
Use text to video for new scenes, ads and stories. Use image to video when you already have the picture, like your own photo, product shot or artwork. Image to video gives the most control over how things look.
Which AI is best for video with sound and dialogue?
Veo 3.1 and Sora 2 create voices, sound effects and music with the picture. Kling 3, Seedance 2 and Grok Imagine also make sound. Hailuo makes silent video at great value.
How long can each clip be?
Veo makes 8 seconds per clip, Sora up to 12, Hailuo and Grok up to 10, and Kling and Seedance up to 15. The timeline warns you when your shots add up to more than the model allows.
How do I stop AI video looking fake?
One clear action per shot, a named camera move, real light and sound, and real-camera feel like micro handheld shake and natural motion blur. For image to video, keep motion subtle so faces stay the same.
What is a shot list?
It breaks the video into shots with a size, camera move, length and action, for example a wide tracking shot, then a close-up push-in. It makes short ads and stories feel edited.
