TutuCut

Say one sentence, get an edit

Drop in footage, say one sentence — trims, captions, music.

People often say Make a 10-second birthday greeting with colorful balloons floating upCut the first 10 seconds and add a title cardAdd subtitles to this clip

Cut this 2-minute clip to 30 seconds on the music beats, and add a title
Your browser is drawing this frame right now

You say:

Cut this 2-minute clip to 30 seconds on the music beats, and add a title
  1. Find the music beats
  2. Split into 8 parts on the beats, drop the dull ones
  3. Add the title
  4. Export the 30-second video

No video-generation model and no queue: the AI writes a timeline, and your browser draws it.

The AI can’t: generate real live-action footage · fix blurry video · remove existing watermarks · create a 3D model file from nothing

Tell the assistant what you want done and it does it: cut the silences, add captions, tighten the pacing. Every AI action is just a message and a reply. Free, no account.

Knowing what you want and knowing which buttons produce it are two different skills, and only one of them is about the video.

Say "cut the parts where nobody is talking and add captions" and it happens on your timeline. There is no separate AI mode — it is the same project you were already editing.

Everything it does is a normal, undoable edit. If you do not like it, undo it, or say what to change instead.

FAQ

Can it undo what it did?
Yes, every AI action is an ordinary edit on the undo stack.
Does it work on a video I already have?
Yes, that is the main use.
How specific can I be?
Very. "Make the second half faster" and "cut everything before the door opens" both work.
Is my video uploaded to the AI?
No. The AI works through the project’s structure, not by sending your footage anywhere.
Is it free?
Yes, with the exceptions named on the "how free it is" page.

Related tools