Video Studio

Brief, script, render, review, publish, and what the video did afterwards – all on one document. Every video keeps one copy in your library, where the calendar, the social scheduler and your reports pick it up.

Open it from Studios → Video Studio, or ask for a video in chat and it lands here. There is one video studio: an older link or bookmark to Instant Video, AI Video Studio, Instant Ads, the Shorts Generator, the UGC Ad Generator or Video to Shorts opens Video Studio at the format that does that job, and anything you asked an agent to make with one of those names still runs here.

Start with a look

The first screen opens on the look – what kind of film this is – and shows it as one. The chosen look plays large on the right, with what it is in a line and the facts that set it apart: how long a beat is, who speaks, which captions, who can be in it. Every other look sits in a row under it, and Change opens them all at once: Someone talking, Product in action, Near-miss selfie, Composed story, Cartoon, Musical cartoon, Message thread, Story from a post, Brainrot, Camera path, and Clips from a long video. The examples were made in this studio for a sample brand; yours is made from your brand, your words and your cast.

Then say where it starts. Start from offers what the look can be made from – a brief, a prompt or an article – and the fields under it are the ones that start needs. Your actor and your product sit under In the film.

Put yourself in it. Beside Actor, the Person tile adds a real person from one photo of their face – you, your founder, anyone who agreed to it. Upload the photo; the studio reads it and writes how they look, which you can edit. Tick the line confirming you have the right to use their likeness in videos for this brand, and Add to the film. Reading the photo costs about 1 credit (a photo it declines, such as one with more than one face or with a child in it, costs nothing), and adding them costs 2 credits for one picture. They join the brand's cast in the Actor Library, so next time they are one click away. A film has one person on camera: choosing an actor replaces them, and the other way round. The model, the length, the shape, the resolution, the captions and the setup are one tile each under Settings; each shows what is chosen and opens the choices. How it works on the right draws the plan for what you have set, one band per beat, names every step and prices it line by line.

Your own videos are under Your videos, beside the examples.

A brief. Start from what you know about the product and the customer. The studio builds a research brief – who buys, what the competition misses, why this product works, what changes for the person – then writes five scripts, one per hook, and you pick the one that sounds like your brand. The scripts become scenes that render, caption and publish as one video.

A prompt. Describe the video in your own words. The studio reads the intent and writes the generation prompt the model needs, with your brand and language carried through. Add a first frame if you have one. A short idea stays one shot; anything from twelve seconds is broken into beats. A message thread and a story from a post are not made from a prompt: their story is the words on screen, and a prompt makes the pictures only.

More than one face. On a brief, pick more than one actor and the studio writes one script and makes a variant per actor, each its own document with its own review and its own performance history, so you can compare them and publish the one that works.

An article. Bring a link, paste the text, or pick an article this brand already published. The studio reads it, finds the claim worth hearing out loud, and retells it as a short: a headline hook, a few beats, on-screen text and captions in your brand colours. Nothing is said that the article does not say. If the link is dead or behind a paywall, the studio tells you on the spot rather than three steps later.

A link to your own site is written as an ad; a link to an article is retold. The studio reads the page and says which it thinks it is, in one line under the source field, before anything is bought. A home page, a pricing page or a feature page is your own writing, so the scripts are allowed to make the case, take a position and ask for something, and they still may not say a single thing the page does not say: no invented number, no promise the page is careful not to make, and the ask comes at the end rather than the opening. Somebody else's article is retold exactly as before, in its own stance, with the publication named once. If the studio reads your page the wrong way, the same line lets you say so in one click, and your word wins.

The five scripts are five different things. Each one owns a different facet of what was read – the idea, the moment it matters, the proof or the caveat, how it works, and the offer – and the studio says which on each card. Five doors into the same three facts is not five scripts, so when two of them come back saying the same thing, one is rewritten before you ever see it.

A camera path. You direct the camera. Pick Camera path and the right side becomes a Stage: your product's stand-in in the middle of a plain room, and a dome of camera places around it. Click the places in the order the film should pass them – each becomes a numbered camera, and the path is drawn through them in that order; click one again to take it out. Two to six cameras, each Wide, Medium or Close. Drag to look around. The small frame in the corner shows what a camera sees in your video's shape, and Play the path flies the whole move.

Above the stage, choose what stands In the middle: Bottle, Can, Jar, Box or Tube, so every camera frames it at the right size, or Person – and for a person, whether they Stand still or Walk forward. A walking person walks on the stage, an arrow on the floor shows where, and your cameras travel with them, so the video shows the walk with your camera move around it. The stage is only for placing the cameras – the place in your video is the one you write under Describe the scene: where it is and what happens, such as "a modern corporate office in soft morning light; she smiles". Add the product's picture under In the film – or, for a person, pick them from your cast or add yourself, and add what they hold. Nothing is said in these videos, so there are no captions; music plays under them.

When you press Render, the studio films the flight on the stage and hands that clip to the model with your picture. The video is one continuous move along your path. SeeDance 2.5 is the default here: it builds the scene you describe and follows the path closely. MiniMax H3 is the choice when a cast member's exact face matters: it keeps their face, takes more of the setting from their photo and follows the path more loosely. Either follows your path the way a camera operator follows a shot list – closely, not to the centimetre. SeeDance never receives a photograph of a real person, so a cast member is described to it in words.

Clips from a long video. This one is a look of its own, because your footage is already the look. Bring a webinar, a talk or an interview. The studio transcribes it, reads the transcript for the passages that stand on their own, cuts them to the shape you publish in, and captions them. Every clip is your own footage and your own words. Its length setting is the length of each clip, and no model is involved, so none is offered.

The scripts

For an ad from a brief and for an article, the studio writes five scripts, one per hook. Read them aloud – the one that sounds like a person is the one that performs. You can edit the dialogue inline before you commit to one.

Each scene shows how many words fit the time it has. A script that runs long is trimmed on the hold at the end, never on your words.

Credits

The estimate is under How it works before you press anything, broken down line by line. Scenes are charged one at a time as they render, and a scene that fails is refunded. Cancel a render and everything unrendered comes back.

Fixed steps:

An actor is made once and used forever, so it is charged once. In the Actor Library every cast member is a character sheet: one picture of one person from every side – five full-length turns (front, three-quarter, profile, turning back, back) above three portraits in three expressions – drawn in a single pass so all eight are unmistakably the same person. We cut the eight views out of it and draw a portrait from it, and those are what every film you cast them in receives, so the face, the build and the wardrobe hold from the first shot to the last.

New character starts with a few words: a role and a feel is enough ("a charismatic, slightly eccentric campaign director in his mid-thirties"). A casting director writes the rest – who they are, the signature look that makes them recognisable at a glance, what they wear from head to toe in your brand's colours, how they come across on camera and the three expressions – and makes them unlike anyone already in your cast. You can settle gender, age or style yourself, or leave them open. Writing the character costs about 1 credit. Every word lands in a form you can change, and nothing is drawn until you press Draw character sheet, which costs 5 credits for the sheet and the portrait; if the picture does not come back, the credits do.

Open anyone in your cast to see their sheet, everything a film receives, and their words. Changing the words changes what every future film says about them, never a picture; Redraw sheet (5 credits) draws the same person again with the words as they are now. Cast members made before character sheets keep working as they are and show Draw their character sheet, which writes their character from who they already are and draws them from their own portrait.

An actor from a photograph. If the person you want in your videos already exists – your founder, your presenter, a model you have hired – choose From a photo under New character and upload one picture of one person. We read the photograph and write the character from it: their face stays exactly theirs, and their outfit follows the photograph unless you say otherwise. Reading the photograph and writing the character costs about 2 credits, and nothing if we decline to read it. We describe what is visible and nothing else: we never guess where someone is from, how old they really are, or anything about their health or who they might be, and a photograph with more than one face in it, or with a child in it, is declined with a plain sentence instead of a description. Before the sheet can be drawn you confirm one line – that you have the right to use this person's likeness in videos for this brand – and we record that confirmation, with its date, on the actor itself. The picture you uploaded stays on the actor as the strongest likeness we hold, and every film you cast them in is built from it.

Rendering is charged per second of finished video, rounded up per scene. The rate is the model and the resolution you render at, because that is what the model charges us for: a second of 1080p costs more than a second of 720p on the same model, up to twice as much. Both are on the Model and Resolution tiles, and each resolution shows its own rate.

Wan 3.0 is the default: a new video opens on it, and so does a video asked for in chat unless you name another model. SeeDance 2.0 opens at 1080p and Kling V3.0 Std renders 720p. Wan 3.0 Prime is Wan in its fast mode, and HappyHorse 1.1 is Alibaba's newest model, slower to render and very clean. SeeDance 2.5 holds the longest takes, up to thirty seconds in one clip, at 480p or 720p. MiniMax H3 is offered on the Camera path look only. The budget models open one rung down, at the resolution a feed actually plays, so the cheap seat is cheap: fifteen seconds on Wan is 30 credits, and the same fifteen seconds on SeeDance 2.0 is about 113.

A twenty-second video in three scenes is three charges, not one.

A fast style buys one clip per beat. A brainrot cut is a beat every few seconds, and the studio buys each beat as its own clip, which is where the hard cuts of that style come from – asking a model to make the cuts inside one clip does not work, because video models render one shot whatever the prompt asks for. Wan renders any length from two seconds and Kling from three, so there each beat is rendered at its own length – but both models charge for at least five seconds of any clip, so a two-second beat costs what five seconds do. SeeDance's shortest clip is four seconds and MiniMax's five: there a shorter beat is bought at that length and cut back to the beat in the edit, and the estimate says both numbers in words – eight two-second beats on SeeDance is "8 beats · 32s bought" for a film that plays for sixteen seconds. Each beat's line is timed to finish inside the seconds that are kept, and if a model is still talking where the cut falls, the cut moves to the next pause rather than through a word.

Styles whose beats are already long enough (Someone talking at five seconds, Composed story at six) buy exactly what they play, and nothing is cut back.

One voice for the whole film. When somebody talks on camera, the video model still performs every line, so the lips stay in sync, and the studio gives the film one ElevenLabs voice across every beat instead of a voice that changes at each cut. When nobody talks on camera, a narrator reads the script over the film in one take, and the captions follow the reading word for word. Pick the voice under Settings: Auto chooses one for your brand's language and the person on camera, or listen to the voices on offer and pick one, or keep the video model's own. A cast member in the Actor Library can carry their own voice, and every film they are cast in speaks with it. It costs 1 credit a film, and if the voice cannot be made the film is delivered with the model's own and the credit comes back.

Music is on by default. Every film gets one instrumental track made for its look – warm and understated under someone talking, bright under a product in action, a solemn drone under a brainrot chant – set under the voice and stepping back while anyone speaks. It is one track for the whole film, never music from the video model, so it does not restart at every cut. It costs 2 credits a film, and the Music tile under Settings turns it off. A long video you cut into clips keeps the sound it was recorded with. If a track cannot be made, the film is delivered without it and the 2 credits come back. A Musical cartoon's music is a song instead (below).

Product in action is bright and moves. Films in this look are set in bold, saturated colours and bright light, and every beat has one effect made by the camera or the action inside the shot: a fast push-in on the product at work, a quick orbit around it, a low angle as it is lifted, or the most satisfying moment in slow motion. Slow motion is kept to beats where nobody is speaking.

Composed story is bright and fresh. Its places and clothes are written in soft, bright pastels (mint, peach, lilac, butter yellow, sky blue) in airy daylight, so the film feels refreshing rather than moody. Cartoon is drawn in the same bright pastels.

A Musical cartoon sings. Your product becomes an original cartoon mascot with a face and a deadpan attitude, doing one meme gag a beat: a stare straight into the camera, a smug dance, a slow turn, a proud freeze. The script's lines are the lyrics of an original song made for the film and sung in your brand's language, with your brand's name sung clearly. The film cuts to a new gag on every line of the song, and every sung word pops up on screen in a white chip as it is sung. There is no voice to pick, because the song is the voice, and its music stays on: the song costs what a music track does (2 credits). The mascot is always an original design, never an existing character.

Brainrot is the internet's own. Your product, cut out like a photograph with a meme face pasted on it, floats through rainbow kaleidoscopes, cosmic tunnels and grids of its own copies, while a narrator solemnly chants its made-up name and its ridiculous story, one line on every cut, and ends on your point. The chant is in your brand's language, the ritual is invented (never a real prayer or mantra), and nothing in it is an existing meme character.

A reference costs one image a shot. When you give a film a product or a mascot to show, the studio draws each shot's opening frame with the thing placed in it and hands the model that frame, rather than handing over the picture and hoping. That is one image per beat at 2 credits, listed on the estimate as its own line. You can turn it off where you chose the product, under In the film; the picture then goes to the model as it is, which is cheaper, and the thing tends to arrive as a sticker in the corner rather than an object in the room.

A brand that has reached its credit budget for the period is told so, with who can raise it – that is a different thing from an empty wallet, and the studio says which it is.

While it renders

The render runs on our side. Close the tab, come back later, open the video from the list or from your library – the page picks it back up. Each scene shows its own state: queued, with the model, rendering, done. A single scene that fails can be retried on its own, and a retry never re-buys a scene that already landed.

Captions and presenter

Captions are burned into the finished video by us, after the scenes are rendered. The studio listens to what was actually said, measures when each word is spoken, lines it up with the script, and writes the words onto the picture in your brand colours, each one on screen as it is heard. Four styles: Word highlight (one line at a time, the spoken word lit as it is said – the short-form default), Clean line (a quiet subtitle, no highlight), Bold centre (two or three words, centred and large, for a video watched with the sound off), and Word chips (every word pops up in its own white chip as it is sung or said, a line at a time, high in the frame – the way a meme sound shows its words, and the Musical cartoon's own).

Captions and reframing also work on a video you already have. Ask in chat to caption or recrop a film that is already in your library and it happens on that video, at the prices in the table above – there is no need to render a second one.

Presenter is who says it. On an article you can leave it empty and the short runs text-led – on-screen text and captions carry the piece, and nobody appears. From a brief the same slot is called Actor: pick a face from your Actor Library and it holds across every scene. Both sit under In the film. Every model in the studio speaks the script itself, Hailuo 3 Max included.

Reference is what every shot has to show, which is a different question from who is in it. Pick A product and the film keeps the same product through every shot, unchanged in shape, colour and label; pick A mascot and it keeps the same character, one design in every shot. The picture can come from your catalog, from an image this brand already has, or from your own upload, and the choice works under every style: a cartoon draws the mascot from it instead of inventing one, a message thread puts the product in the footage behind the card, and a presenter holds it up. Where the model you chose has only one image slot and something else is already in it – your presenter's photograph, or a first frame you picked – the studio says so on the row and keeps the product in the direction it writes. A first frame you picked holds only the opening shot, so the picture still reaches every shot after it, and the row says that too. The picture has to be this brand's: one from another brand's library is refused rather than filmed.

Review

The Review tab carries the video's status – Draft, In review, Changes requested, Approved – and the comment thread your library uses: @-mention a teammate, reply, resolve. Approval is off by default and is turned on per brand under Brand → Messaging, where you also choose who approves. With it on, a video is approved before it can be published.

Publish

The Publish tab posts through the accounts this brand has connected: YouTube, TikTok, Instagram, Facebook, LinkedIn. Accounts on your other brands are not offered here – a video publishes through the brand it belongs to.

Write one caption and the studio adapts it per platform. Publish now, or pick a time and it lands on the calendar, where it can be moved or cancelled until it goes out.

Each platform asks for its own things, and the studio asks before it sends rather than after:

• YouTube needs a title of 100 characters or fewer. A vertical video under three minutes posts as a Short.
• Instagram Reels need a cover frame. A frame from the video is offered; without one the platform picks the first frame.
• LinkedIn posts as the page or as the person, chosen at publish time.
• TikTok is the one that sends you elsewhere. Who can see the video, the preview confirmed, and your consent are the creator's own choices, and TikTok requires them to be made deliberately. The studio never guesses them: it hands you to the social composer, you make the choices there, and the post goes out from there. A TikTok publish with those settings missing is refused, not defaulted.

Videos published from here also declare themselves as AI-generated where the platform asks: YouTube's synthetic media flag and Instagram's AI label are set for you.

Performance

The Performance tab shows what the video did once it was out: views, watch time, average view, engagement, and clicks on the links in the caption. Underneath, the accounts around it over the last 28 days – labelled as account numbers, because a channel's watch time is not this video's watch time.

Platforms report on their own schedule, so a post from today may still read nothing. A number nobody reported is shown as not reported, never as zero – those are different facts. Where watch time had to be worked out from a platform's own retention curve, the tab says so and names the platform.

Limits worth knowing

• An actor batch opens on the first variant. The rest are made at the same time and sit in your video list, grouped together; there is no side-by-side comparison screen yet.
• An article has to be readable. A page that hides its text behind a login, a paywall or a script-rendered shell may come back empty or wrong. Paste the text instead when that happens.
• Chat and the autonomous team quote a rough price. A video asked for in chat shows an estimate for one short scene; the real charge is per scene and can be higher. The estimate under How it works is the accurate one.