TutuCut

Make an animation with AI

One sentence makes an animation: motion graphics, 3D, a character that walks and talks, bones and frame-by-frame drawing.

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

Make a gold gift box spin once, then show “New arrival”
Your browser is drawing this frame right now

You say:

Make a gold gift box spin once, then show “New arrival”
  1. Create a 3D scene
  2. Add a gift box
  3. Give it a gold metal finish
  4. Add two lights
  5. Spin it once
  6. Show “New arrival”

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

Say one sentence and the AI makes an animated video in your browser — no footage, no sign-in. Motion graphics, 3D scenes with physics, a character that walks and talks to your voice, bone rigs and frame-by-frame drawing, all on an editable timeline. No live-action footage, no stock character library. No watermark.

Making animation used to mean being able to draw or knowing the software. Here you say what you want in one sentence — say, “a 10-second birthday greeting: colorful balloons float up, then ‘Happy Birthday’ appears” — the AI writes it as a timeline, and your browser draws it on the spot, with no queue.

What it can make: motion graphics (rectangles, circles, SVG paths that draw themselves on, text — with keyframed position, rotation, scale and opacity, and easing); 3D scenes (basic shapes, materials, lights, camera moves, and physics such as drops, collisions and bounces); a walking character whose mouth follows a voice you add; bone animation; frame-by-frame drawing; plus 6 ready-made templates and text entrance animations.

What you get is an ordinary project: every shape, keyframe and line of text can be dragged and changed by hand, or you can keep going with “bigger text” or “make the balloons blue”. To be clear about the limits: it does not generate live-action or photographic footage, it has no stock library of characters, scenes or props, and it cannot turn a photo into a character automatically.

FAQ

What does it look like?
Drawn: flat shapes, drawn-on lines, text, or 3D basic shapes and models you import. It is not photographic realism — that would need a video generation model, which this site does not run.
Can a character walk and talk?
Yes. There is one simple built-in 2D character that walks or runs along a path with its feet planted; add a voice you recorded or imported and its mouth follows it. Its colors and shapes can be changed, but it is a single built-in character, not a character library.
Can I use my own drawings?
Yes. You can draw frame by frame, or attach parts you drew to bones and pose them; for 3D you can import your own .glb model. What it can’t do is turn a photo into a moving character automatically.
How long does it take? Is there a queue?
No queue. Once the AI has written the timeline your browser draws it on the spot, usually within seconds. 3D and physics need a browser with 3D acceleration (WebGL).
Is it free? Is there a watermark?
Free, with no sign-in, and MP4 and GIF exports carry no watermark. The AI chat needs an internet connection; its usage allowance is whatever the assistant shows.

Related tools