Skip to content

Make a UGC ad from a script

Write what happens and the lines they say, add a presenter, your product or a place if you like, and press Make the video. Or, under Advanced, pick Step by step to see previews first, pick one, then make the video from it.

Updated · 11 min read

On this page
  1. 01Make an ad
  2. 02Step by step: a preview first
  3. 03Voices
  4. 04Real people
  5. 05Templates
  6. 06What it costs
  7. 07When it's made

UGC ads are made on UGC Ads: a creator-style video of someone talking to camera. Only the words are needed. A presenter, your product, a place, a video to follow and the voices are all optional, and anything you add can be named in the words.

Make an ad

  1. Write the words. Say where it happens, what they do, and the lines they say in double quotes. Only the quoted lines are spoken; if nothing is quoted, everything you wrote is read as the script. Under the box, a count shows how many words they say and about how long that takes. Improve the words, beside it, writes a short script out in full: where the phone is, what the hands do with the product and how each beat ends. It keeps your quoted lines and the names you typed word for word, and follows the skills you have on, such as AI actor ads. It shows the most it can cost, you pay what it uses, and Undo puts your own words back.

  2. Add what you want in it. Each group above the words is optional, and each tile shows the name you call it by:

    • Presenters: someone from your Cast, a picture from your Library, or your own character, in one picture or up to four. A video of them works too: a still is taken from it. An ad takes up to four presenters, each called by their name: a cast member by their @name, such as @Amara, and your own character by the name you gave them. One with no name is @presenter1, @presenter2 and so on. Two with one name are told apart: @Amara and @Amara_2.
    • Product: up to three pictures of your product, called @Product1, @Product2 and @Product3. Say its name and what it does in the words.
    • Place: up to three pictures of the room, a prop or a look, named @Image1 and on. Or say where in the words.
    • Look like: a video for the model to follow, its look and its pace but not the people in it, named @Video1.
    • Voices: optional, one for each presenter (see below).
  3. Name them in the words. Type @ to pick from what's in the bar, by name: "@Amara holds up @Product1". Words you paste from an older ad that say @Presenter1 are matched to the bar and show as their names. A cast member's @name is the one every studio calls them: rename it on their tile in Video or Images, or in your Library.

  4. Pick the video model. The Video chip lists the models in two groups: Speak the words with the picture (Seedance, Kling 3.0, Kling 4.0 and Kling 4.0 Flash), and Lip-sync a voice exactly, which moves one face to a voice. Each model's line says the longest take it makes and its price a second. On the free plan, when your credits can't cover a usual ad on Seedance 2.0, a new ad starts on Seedance 2.0 Mini at 480p. Hover over a model and the panel beside the list says what to pick it for and when to skip it. A new ad starts on Seedance 2.0, marked Recommended.

  5. Set the shape, size and length. Shape and Size list only what the model makes. Length starts on Fit the words, the shortest length that holds what is said; pick a length instead to make one take of exactly that. A lip-synced clip lasts as long as its voice. ×1 to ×4 sets how many takes one press makes, each its own video from the same inputs.

  6. Choose the AI label. AI label in the bar puts "AI-generated" on every frame, top left. A new ad starts with it off: then say it was made with AI where you post it. See Captions and the AI label.

  7. Change Advanced if you like. A new ad needs nothing from it. Advanced holds:

    • How it's made: One shot, where a new ad starts: your words and pictures go straight to the video model, in one press. Or Step by step: previews of your video first, for their own price, then the video from the one you pick (see below).
    • With Step by step, Previews to pick from: how many previews each take draws, 1, 2 or 3, each at a picture's price; it starts at 2. And Previews made with: the model that draws your presenter with the product in the place. The five listed first keep faces and product labels best: Seedream 5.0 Pro (Recommended), Nano Banana 2.1, GPT Image 2.5 (the one for small print on a label), Nano Banana Pro and Nano Banana 2. More picture models are listed under them.
    • Captions: your words captioned on your presenter, their style, size and place: see Captions and the AI label.

    A dot on Advanced means something there isn't as a new ad has it, such as Step by step; Reset puts it back. Whichever way you pick stays for your next ad. On a phone, Advanced is at the foot of Settings, and the settings line says Step by step while it's on.

  8. Press Make the video, or ⌘ Return (Ctrl Enter on Windows) in the words. With Step by step it says Preview my video; with more than one take, Make the videos or Preview my videos. It appears first in My ads, and the bar folds to one line so nothing covers it: Open the bar brings it back. The words clear for the next one; everything else in the bar stays.

In One shot the video model takes your pictures as they are. Where it can't, a first frame is drawn from them on the way, without stopping: for a real person, whose face no model takes as a reference, for Kling 3.0, which takes no references, and for a lip-sync with no presenter to move. The line under the bar lists that first frame with its price.

Step by step: a preview first

Your video starts from a picture: the face, the product and its label, and the place. With Step by step, Preview my video draws previews of that picture first, two to pick from, for the pictures' own price, and waits for you before the video is made.

  1. The previews are made at the top of My ads, under Step 1 of 2, while the bar folds out of the way.
  2. When they land, tap the one your video should start from. Then press Make the video: the button shows what the video costs. It says Starting your video… for a few seconds, then the ad's tile shows Step 2 of 2 while the video is made.
  3. If something is off, press New preview to draw the one you picked again, for a picture's price, or Change the words, which opens the bar.

Nothing more is charged until you press Make the video. If you leave first, the ad waits in My ads with Pick a preview (Check the preview where it drew one), which opens the same pick. With several takes, each draws its own previews, and Make the video makes every take, each from the one you picked.

If something holds the button, the line under the bar says what, such as "Say who is in your picture, and tick that they agreed." A script too long for one take is never refused: it's made in parts, joined into one video. See Long scripts: how an ad is made in parts.

Voices

A voice is optional. A model that speaks the words makes the sound itself, saying the lines you quote, so every presenter starts on the model's own voice. To choose how someone sounds, press their tile under Voices. ▶ plays a voice before you pick it. To take a voice out, press × on its tile: they go back to the model's own voice.

  • The model's own voice: the video model voices it from the words.
  • Their own: a Cast member's own voice, where they have one.
  • A voice from the list, which you can filter and search.
  • Record it now: up to 30 seconds, in your browser.
  • Upload a recording: WAV or MP3. You're asked whose voice it is.

Voices offers only what the video model takes:

  • Seedance takes any of them.
  • Kling 3.0 takes a Cast member's own voice, kept with their character, and voices everyone else itself.
  • Kling 4.0 and Kling 4.0 Flash take no voice, so Voices isn't shown: they voice the words themselves.

A voice you picked on another model stays in the bar for when you switch back, and the line under the bar says it isn't used. A lip-sync model needs a voice other than the model's own; there, a presenter from Cast starts on their own voice. A recording has to be a length the model takes; if it isn't, the line under the bar says so.

Real people

A photo or video of a real person can be used only with their permission. Open the tile, choose A real person, type their full name and tick the statement; for an AI character, a drawing or a mascot, choose that no real person is in it. The button stays off until every presenter, the Look like video and any uploaded recording has an answer. Seedance doesn't take a real person's face as a reference, so an ad with a real person starts from a picture drawn of them: a first frame in One shot, the previews in Step by step. See Real people: faces, voices and consent.

Templates

The Templates tab opens on our own ads, the ones we made to sell Vessero: Skincare and snack, Are you real?, The fridge, Casting call and Which one is real? Use this on one fills the bar with everything the ad was made from: its people, its products' pictures and its whole script, every line as the ad says it. Vera, our own AI actor, comes in as a picture in her own voice; the others come from the starter cast in theirs. What the bar held before is replaced, and your model stays. Swap in your product and your lines, then press the button. Are you real? and Casting call each had one more person than the bar takes (four), so one shot is left out, and a note says which. Each ad's whole board is under Templates on Creative Board.

After our ads come eight formats, such as Unboxing, Problem → solution and Gym mirror, each a script, a place and the person on its cover. Use this puts that person in the bar, from the starter cast, in their own voice, and its words. A model that can't take their voice speaks the words in its own. Your model and your product stay as they are, and nothing runs until you press the button; a note says who came in and what is left to add.

Unboxing shows only hands, so it brings nobody: the model draws the person, or add your own.

What it costs

The price is beside the button: with Step by step, what the previews cost; otherwise the whole ad. Hover over it, or move to it with the Tab key, to see the sum: pictures, clips, voice and the finish. The line under the bar says what one press makes, what each part costs and, with Step by step, what the video costs once you pick a preview and the whole ad together. Each take is charged its own clip and finish, which cuts it together and adds the captions when you pick a style, and its previews or first frame where it has them; a voice read for the ad is made once and heard in every take, and a recording you bring adds nothing for the voice.

You're never charged more than the price you pressed at. If the price has gone up since the page loaded, you're shown the new one and asked to press again. If your balance is short, the button opens a window with the price and the plans, with Pro marked Recommended and Ultra marked Best value, and your own offer on them if you hold one, or credits once.

When it's made

While an ad is made, its tile in My ads shows the stage it has reached, naming the model: its first frame or previews where it has them, the clip, then the finish, shown as Captions. With Step by step it says Step 1 of 2 while the previews are made, waits at Pick a preview until you press Make the video, then says Step 2 of 2. It's made on our servers, so you can close the page.

A finished ad plays where it sits, with sound: press ▶. Open it to play it larger, switch between takes, Download it, or press Use again to put its words, people, product and settings back in the bar. Delete removes it for good; our team can still see it for 14 days, to check it against our rules, before it's erased.

Under its takes, References shows what the ad was made from, each by its place in the ad and with its name: each presenter (@Presenter1, with their name), the product's pictures (@Product1), your other pictures (@Image1), the video to look like (@Video1) and any recording you brought (@Audio1). Press one to see or play it where the ad plays; Back to the ad, or Esc, brings the ad back. A voice from the voice library isn't listed: there's no file of yours to open.

A take that fails says why. The credits for the step that failed come back automatically, and the steps after it aren't charged: see My video failed. Did I lose my credits?

Was this helpful?

Still stuck?

A person reads every message.

Usually within 4 hours on a working day. support@team.vessero.com