Your video alreadyhas the story.Cueits draws it.
Upload a talking-head short. Correct what the transcript misheard. Say in one sentence what the panel should argue. Every graphic lands on the exact phrase that motivates it — not near it, on it.
Almost all code is already AI they ask one thing first ninety five percent of it having the agent isn't the skill start with what you can finish
You approve the argument
before it costs anything.
The video is broken into beats — one idea each, every one pinned to a verbatim quote from your transcript. You see the whole plan and what each beat is anchored to first. A misreading gets caught while catching it is still free.
Almost all code is already AI they ask one thing first ninety five percent of it having the agent isn't the skill start with what you can finish
Pick a row. This is the panel that beat produces, and the moment it arrives is the moment “AI” is spoken.
Authored demonstration content.
Three answers.
One render.
The brief is collected as a conversation, one question at a time. Nothing about it lives in your browser's memory — a render survives a reload, a closed tab, and navigating away.
- 1
Upload the take
Any talking-head short between 5 and 600 seconds. Cueits transcribes it word by word, and every word carries its own timestamp.
MP4 · MOV · WEBM · MKV · ≤100MB - 2
Correct and aim
Fix what the transcript misheard — it mishears proper nouns and jargon most, which are the words a point usually turns on. Then say in one sentence what the panel should argue.
Highest-leverage 30 seconds you'll spend - 3
Pick a look, render
Thirty-one visual systems, previewed live while you hover. About two minutes of machine time later, a finished vertical video lands in your library.
MP4 · ready to post
Different looks.
One mechanism.
Every tile below is playing the same sentence, off the same clock, and every one fires on the same word. Each draws that moment with its own elements, its signature ones first. Choosing a preset changes what the panel is made of. It changes nothing about when the panel happens.
- Torn Paper Digest33Awaiting anchor
- Soft Window32Awaiting anchor
- Notepad Carousel31Awaiting anchor
- Marker Highlight28Awaiting anchor
- Dot Matrix29Awaiting anchor
- Sticker Travel27Awaiting anchor
- Swiss Grid23Awaiting anchor
- Weather Bulletin22Awaiting anchor
- Transit Sign17Awaiting anchor
- Cinematic16Awaiting anchor
- Neo-Brutalist15Awaiting anchor
- Broadcast09Awaiting anchor
- Dark Terminal03Awaiting anchor
- Arcade Pixel20Awaiting anchor
Or just say what you want. “Dark and techy” is a valid answer to the preset question.
Demonstration content. The preset names, palettes, type and elements are the product’s own; the sentence and figures are authored.
Built for the frame
it will be watched in.
Vertical by default — the native Shorts, Reels and TikTok frame, not a landscape video with bars and not a square hedging between the two. Landscape renders too, with the panel beside you rather than above.
- The panel owns the top 55%
- Generated, not templated: type, charts, lists, quotes, stamps, terminal output — whatever the sentence being spoken calls for. If a slot has nothing true to put in it, it stays empty rather than getting filled with fiction.
- You own the bottom 45%
- Cropped from your own upload and otherwise untouched. The crop is centred on where a seated talking head's face actually sits rather than the middle of the frame, so nobody gets decapitated, and it is rotation-corrected so a phone shot sideways lands right way up.
- Captions sit on the seam
- High enough not to cover your face, low enough to read as belonging to you rather than to the graphic. Three styles, and off is one of them.
- Your audio, untouched
- Nothing is re-encoded, ducked or normalised behind your back. A silent video still renders.
Your video already contains
the argument.
The visual layer is the part you can't afford to make. There are two other ways to get one, and it is worth being precise about what each actually costs you.
An editor
A timeline, and you place every graphic on it by hand against a waveform.
- Time per video
- About an hour
- Synchronisation
- Exact — if you do it
- The look
- Whatever you build
Accurate, and you will not do it every week.
A template tool
Motion graphics with slots. Fast, and the audio may as well not exist.
- Time per video
- Minutes
- Synchronisation
- None
- The look
- The template's
Quick, and it argues nothing in particular.
Cueits
AutomaticThree answers. Every reveal pinned to a verbatim quote from what you actually said.
- Time per video
- ~2 min of machine time
- Synchronisation
- Anchored to the word
- The look
- Thirty-one systems, or describe one
The visual layer, at the cost of answering three questions.
Start free.
Pick a plan when
you outgrow it.
Free is not a trial and there is no clock on it. Two videos and three caption videos every month, exported at 720p. What paying buys is the watermark coming off, 1080p, longer videos, and more of them.
Free
$0/moThe real product, three times, with the mark on.
- Credits
- 100 / month
- Max source
- 1 min
- Watermark
- yes
Starter
$19/moFor a weekly posting habit.
- Credits
- 1,000 / month
- Max source
- 3 min
- Watermark
- none
Pro
$49/moFive minutes, 2K, higher in the queue.
- Credits
- 2,600 / month
- Max source
- 5 min
- Watermark
- none
Studio
$129/moFor a team shipping every day.
- Credits
- 7,000 / month
- Max source
- 10 min
- Watermark
- none
Worth knowing up front
The things people ask before they upload anything, answered here rather than in a support thread.
- What is Cueits?
- Cueits turns a talking-head video into a finished MP4 with a generated infographic panel above the speaker — charts, statistics, lists and quotes composed from the transcript, each revealed on the exact word that motivates it. It also makes word-level animated captions. A video takes about two minutes of machine time.
- Do I have to design anything?
- No. You pick one of thirty-one looks and Cueits composes the panel from your transcript. What you can change afterwards is the content — the wording of a line, the figure in a statistic, which element a beat draws, where a beat starts — not the layout.
- Does Cueits generate the video or the voice?
- Neither. The only footage in the output is your own recording, and Cueits never writes words for you to say. There are no avatars and no synthetic voice. The panel above you is the only thing it draws.
- What if it gets a fact wrong?
- Every panel is reviewable before you spend a render on it, and nothing is invented to fill a gap — an element with no real figure behind it is left out rather than filled with a plausible one. Correcting the transcript first is what stops most errors, because the panel is built from it.
- What does Cueits not do?
- It does not edit: no trimming, no cutting, no audio clean-up. It does not source b-roll. It does not pick the best moment out of a long recording, and it does not translate — captions are in the language that was spoken.
Say it once. Cueits draws the rest.
100 free credits a month, no card — three finished animations, or five caption videos. Enough to put real work in front of your audience and find out what it does for you.