How to make a short video ad with AI from a prompt

Describe the ad in a sentence, for example "a 20-second ad for Dawn, a coffee shop: four scenes, a narrator and warm acoustic music". Recut breaks it into steps, makes a keyframe and a clip for each scene, the narration and the music, and assembles them into one film, with the models and prices shown first.

Step by step

1. Describe the adSay the length, the shape (vertical for TikTok and Reels), the scenes or the story, the voice and the music. Attach a logo or product photos if you have them.
2. Review the planRecut plans the steps and wires each result into the next: each scene's image becomes its clip, and the clips, narration and music become one film. Every model step shows the best models side by side with their prices.
3. Run itApprove each run yourself, or let Recut work through the plan within a spending limit you set.
4. Fix one partEvery image, clip and sound is kept on the timeline. Redo one scene with another model or new words, and reassemble without starting over.

What Recut does

The final assembly runs on your device: clips in order, each scene's narration over its clip, music under everything and turned down while the narrator speaks, all fitted to one size, with even loudness at the end.

Recut searches the fal and Replicate catalogues and providers such as ElevenLabs, Google and OpenAI for each step, so the video, voice and music can come from whichever models suit that step best.

Tips

• Be specific about each scene; Recut writes the model prompts from your words.
• Ask for captions and an end card in the same request to get a post-ready video in one plan.

What it doesn't do

• The look and motion of each clip are the video model's; expect to redo a scene now and then.
• There's no manual multi-track timeline to drag clips around: changes are asked for in words.

Related guides

• How to make a product video ad from one photoRecut's Product shot to ad template turns one product photo into three lifestyle shots and a captioned hero video with an end card.
• How to turn a photo into a video with AIAttach a photo, describe the motion, and Recut animates it with an image-to-video model such as Kling, Veo or Seedance, priced before you run.
• How to add an AI voiceover to a videoPaste a script, pick a voice, and Recut reads it with an AI voice model and lays the voiceover on your video, with music turned down under it.
• How to merge video clips into one videoAttach your clips, say the order, and Recut joins them into one video fitted to one size, even when the clips differ in shape or have no sound.