AI video assistant: it can edit, and it can create
One sentence edits your footage — or makes a video from nothing.
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
How far can the AI go?
First, films made with TutuCut. Then watch one sentence turn into a video on the spot.
Made with TutuCut
The village scenery and the fox are AI-generated illustrations. In TutuCut they were split into parts and rigged with bones, so the fox walks up, bumps into the wall and backs away.
Made with:
- AI-generated illustrations
- Bone animation
- Movement and contact
The assistant can also generate material
- Generate images Describe an illustration, background or photo and it is generated, ready to place on the timeline.
Illustrations generated by AI · camera moves, transitions, titles and subtitles added in TutuCut
- Generate video clips Describe a shot and get a short video clip for the timeline. This one requires signing in.
- Generate audio Generate music or sound effects and cut them together with the picture on an audio track.
These three need an internet connection, and the results are saved to your TutuDrive. Usage limits are shown in the assistant.
Say one sentence and watch it being made
No video-generation model and no queue: the AI writes a timeline, and your browser draws it.
You say:
Make a 10-second birthday greeting: colorful balloons float up, then “Happy Birthday” appears
- Set up a 3D scene
- Add 5 balloons that float up
- Add a cake and falling confetti
- Add the text with a pop-in
- Export the 10-second video
You say:
Bigger text in yellow, and make the balloons blue
- Larger font size
- Color white → yellow
- Balloons → blue
You say:
Cut this 2-minute clip to 30 seconds on the music beats, and add a title
- Find the music beats
- Split into 8 parts on the beats, drop the dull ones
- Add the title
- Export the 30-second video
You say:
Have a character walk in from the left and talk along with this voice clip
- Add a small 3D robot
- Walk to the center and wave
- Drop in a voice clip
- The mouth opens and closes with the voice
- Add subtitles
You say:
Make a gold gift box spin once, then show “New arrival”
- Create a 3D scene
- Add a gift box
- Give it a gold metal finish
- Add two lights
- Spin it once
- Show “New arrival”
You say:
Add a “New arrival” title animation over the gift box
- Add a built-in title motion
- Set the title to “New arrival”
- Export the 8-second video
The AI can’t: generate real live-action footage · fix blurry video · remove existing watermarks · create a 3D model file from nothing
The TutuCut AI does two things: it edits your footage from one sentence, and it builds an animated video when you have no footage at all. Motion graphics, 3D scenes, a character that walks and talks, and text animation are drawn on the spot in your browser — no queue, no sign-in, no watermark.
If you have footage, say “cut the first 10 seconds, add a title card, put some light music under it”. If you have nothing, say “make a 10-second birthday greeting: colorful balloons float up, then ‘Happy Birthday’ appears”. It does both.
Creating from scratch needs no queue because it is not running a video generation model. What the AI writes is a timeline — which shape, character or 3D object appears at which second, how it moves, what text shows — and the engine in your browser draws it.
Anything you can do by hand, the AI can do too. That is not a slogan: a test called manual-parity checks it item by item, and the build fails if something is missing.
Do you already have footage?
Yes — let the AI edit it
FAQ
- Does AI video editing cost anything?
- Editing, creating, talking to the AI to change your video, and typed subtitles are free and need no account. Only letting the AI transcribe what is said (automatic subtitles) requires signing in, because the audio has to go into your TutuDrive first. The AI usage allowance is whatever the assistant shows.
- How long is the queue?
- There is none. Motion graphics, 3D scenes, characters and text are drawn immediately — usually within seconds. Only speech recognition (working out what is said in a video) takes a dozen seconds or so.
- I have no footage at all. Can it really make a video?
- Yes. It can make motion graphics (shapes, drawn-on paths, text), 3D scenes (basic shapes, lights, materials, camera, physics), a character that walks and talks, bone animation and frame-by-frame drawing, plus 6 templates, text animation, 26 filters, 13 transitions and 20 effects. It needs no file from you. What it doesn’t have is a stock library of characters, scenes or props.
- Do AI-generated videos have a watermark?
- No. You get a clean MP4 you can publish directly.
- Can I undo what the AI did?
- Yes. Each AI action counts as one step, so Ctrl+Z works exactly as it does for your own edits.
- Does the AI see my video content?
- Day to day it reads the project structure — which clip sits at which second. When it needs to see the picture — to check its own edit, or because you boxed an area and asked about "this" — it grabs a few small frames in your browser and looks at those, only the frames or the area it needs; the video file itself is never uploaded. Only when you ask it to "listen to this part" is that audio sent for analysis, and it lands in your own TutuDrive.
- Are the AI features the same on mobile?
- Yes. On a phone the assistant is a bottom sheet, and it can do everything it does on desktop.
- What can the AI definitely not do?
- It cannot generate live-action footage of real people, cannot restore damaged video quality, does not do super-resolution, cannot remove an existing watermark, cannot identify people, and cannot handle WMV, FLV or RM files. Without a network the AI is unavailable, though local editing keeps working.