# Utopia Dreams Platform

> Write the script, create characters with the same face in every shot, draw the storyboard, film every shot with video and sound, narrate, score and edit your film with AI. Export, publish or carry on in Unreal Engine and Unity.

Utopia Dreams Platform writes the script, designs the characters and settings, draws the storyboard, films every shot with video and sound, narrates, scores and edits it. And when you want to go further, the story carries on in Unreal Engine and Unity.

- From an idea to a finished film, in one place.
- Shorter pre-production, production and post-production, for any audiovisual format.

## Key facts

- **Product**: Utopia Dreams Platform, an AI film studio that works in the web browser.
- **Made by**: Utopia Dreams VFX, Raúl Bellmunt Tabero's studio in Terrassa (Barcelona, Spain), a member of the Google for Startups Cloud Program.
- **Status**: In beta: you request access and the team approves it.
- **Pricing**: There is a free plan with 300 credits a month and three paid plans: Creador (€49 a month), Pro (€149 a month) and Estudio (€599 a month), which make about 2.2, 7 and 28.2 minutes of finished film a month, 17 % off when paid yearly. Each paid plan starts with a free trial of 18 days, once per person, which you can cancel in one click before the first charge. Usage credits that never expire can also be bought, and the models from other companies (not Google) come in an add-on for the paid plans, one payment of €29. Each AI call spends credits by model and quality, and drafts cost far less than the final take. Prices without VAT.
- **AI models**: The AI models behind Utopia Dreams Platform: Google's Gemini for scripts, Nano Banana for images, Veo 3.1 for video with sound, Lyria for music and Gemini Text-to-Speech for voices; Antton for Basque narration; and the other companies' video and 3D models of the add-on.
- **Languages**: The interface is in English, Spanish and Catalan; stories, voices and subtitles in more than 30 languages.
- **Contact**: hello@utopiadreams-vfx.com · https://app.utopiadreams-vfx.com
- **Not to be confused with**: Utopai Studios or any other company with a similar name: Utopia Dreams VFX is not related to them. Nor with the studio's previous website (www.utopiadreams-vfx.com and www.utopia-dreams.com, until October 2026), whose Essential, Professional and Premium plans and their prices no longer apply: the current ones are above.

## Idea and script

From a sentence or your own screenplay.

- **A whole film, not loose clips**: Script, characters, storyboard, video, voice, music and editing in one app.
  Describe your idea in a sentence or plan it step by step. The app writes the script, designs characters, settings and props with their images, draws the storyboard, generates each shot with video and sound in Veo, narrates it, scores it with Lyria and edits it on a timeline. You direct every step and change whatever you want. Or start from a video: paste a YouTube link or upload an example, and the app studies its look, rhythm and structure to plan yours.
  - Start from one sentence and add your screenplay, reference pictures or a reference video with the + button.
  - Your screenplay's voice-over becomes each shot's narration, word for word.
  - Any length: from a reel to a long film.
  - Time and credits shown before anything is generated.
- **See what's possible, and a 30-second demo**: Example films to start from and a whole film made with one click.
  As soon as you sign in, browse films made with the app: film genres, a children's tale, a training video, a vertical reel and LED wall backgrounds. Each one says what it used, and «Make one like this» starts your story from its idea. Or try the 30-second demo: one click and the app writes the script, designs the characters, draws the storyboard, films four shots with sound, narrates, scores and edits them.
  - Each example shows its genre, its mode and the parts of the app it used.
  - «Make one like this» leaves the plan ready, with its cost, in the Pitch chat.
  - The first 30-second demo is free.
- **Dialogue that fits the shot**: Import your script or write it with AI, fitted to each shot's length.
  In each scene you choose who speaks, import the dialogue from a text file (.txt, .md, .fountain or subtitles) or write it in a chat. The AI also adapts a long text, such as a script or a chapter, to what fits in the shot, keeping its best lines and how each character talks. Veo speaks the lines inside the clip, and a character with a fixed voice or a cloned one keeps it in every scene. A shot extended for a long conversation goes on with Gemini Omni Flash, which carries on the clip itself with the characters' sheets, so faces and voices don't change halfway.
  - Understands screenplay layout, “NAME: line” and subtitles.
  - A counter warns when the dialogue doesn't fit the clip.
  - Or the shot fits the dialogue: with «Fit scenes to their dialogue», each scene becomes one continuous shot of up to 40 s that says every word in the characters' voices.
  - The file is read in your browser and never stored.
  - Stories in Basque get Antton, a native Basque narrator (Pro and Estudio).
- **Film-craft skills in the chat**: Fourteen short lessons from film crafts help you shape the story, even with no experience.
  Next to the chat's «+», «Skills» opens 14 short lessons: find the idea, three-act script, conflict and twist, characters, dialogue, tone and genre, world, light, camera, sound, music, rhythm, video for social media and adverts. Each one asks a few questions with examples and options to pick, or suggests the answers with AI from your idea. What you decide travels with the story, and the screenwriter and the storyboard apply it with the know-how of the film crew's roles.
  - Questions with examples and options to pick: no blank page.
  - «Suggest with AI» proposes the answers from your idea, for about one text call.
  - Each skill adds a chip you can open to change your answers.
  - The criteria come from the same film crew that reviews your story.

## Characters and world

The cast, places and props, consistent in every shot.

- **Characters keep their face**: Upload a photo and the character keeps that face in every scene.
  The photo you upload, import from Google Photos or take with the camera is used as it is as the identity reference in every image and shot of the character, with tips to take it well. So the lead is the same from start to finish, even when the setting or the light changes. Once you clone a voice, a small chat suggests other ways for it to speak (happier, sadder, slower…), and the character keeps the one you choose.
  - A face photo and a full-body photo, uploaded, from Google Photos or taken with the camera in the app.
  - References of characters, props and settings in every image.
  - A guide for each photo, with the pose drawn over the camera so it works well.
  - The same clothes, age and height in every scene, and a cloned voice says the character's lines.
  - People who look and move like real people, in places that feel alive: natural skin, blinking and breathing, hair and clothes in the wind, and «Humanize» on any shot, comparing both videos and keeping both versions.
- **A coherence advisor at every step**: It warns before faces, clothes or voices change between shots, and fixes it in one click.
  While you create a story, the advisor (the «Coherence» button in the top bar) checks each step against the continuity rules: a sharp photo of each character, a fixed or cloned voice for whoever speaks, the same clothes, the speaker's face in the first frame, a camera that never leaves them, one take per clip and the same light in each place. Each warning says what fails, why it matters and how to fix it, and «Fix» does it alone when it can, with a before and after you can undo. The rule checks cost nothing; AI can also look for hidden faces in older storyboard images and for cuts inside a clip, showing its credits first. Each new storyboard image also warns you when it has writing in it (a sign, a logo, a number plate), or in a realistic story when a face has waxy, airbrushed skin, before you pay for a clip that would copy it; «Draw again» redoes just that frame. With your memory on, it learns the mistakes you repeat so the writer avoids them.
  - Warnings on each character, each scene and in the editor, and a checklist before «Generate videos».
  - «Fix» in one click: a fixed voice, the clothes sentence, a steady camera, the first shot's light or another model.
  - AI checks for hidden faces, waxy skin in realistic stories and cuts inside a clip, with the credits shown first.
  - Your usual mistakes, learnt with your memory on and deleted whenever you want in Settings.
- **An assistant in every element**: Ask for changes in your own words in characters, settings, props and shots.
  Every character, setting, prop and shot has its own chat. Ask “make it more cinematic” or “suggest another camera move”: the whole film crew answers (direction, writing, cinematography, camera, art direction, costume and make-up, acting, continuity, sound, music, voice-over, editing and VFX), or only the expert you pick, and suggests up to three changes, which you apply with one click. When a change alters the image, it tells you what the new one costs. You can also connect AI assistants such as Claude or Gemini CLI to your stories through MCP.
  - Thirteen film-crew experts: ask them all or just one.
  - Up to three suggestions per message, with their cost shown.
  - Renaming a character also updates the script.
- **Search your library**: Describe a shot, a character or a place and find it among all your stories.
  In Your stories, type what you remember: «the night shot on the rooftop», «the detective in the red coat». The app searches the names, descriptions and prompts of your stories and your team's and shows the stories, characters, settings, props and shots that match, each with its picture. Click one and the story opens right at that element.
  - Your stories and your team's, in both spaces.
  - Results grouped by story, character, setting, prop and shot, with their picture.
  - One click opens the story at what you found.
- **A library ready to cast**: 868 pieces by sector, from training to fashion, banking or tourism: 171 made-up avatars with a reference sheet and a voice in three languages (60 of them cast for a film genre), 141 characters, 345 settings (among them 40 real places in Spain), 159 props and 52 example films, with their versions in other languages.
  «Library», on the rail, opens with a shop window of example films by sector, each one to watch on its own page. Below it is the catalogue: avatars, characters, settings and props, each type with its own filters and sorted for the story you have open, its format, style and language first. Each avatar is a fictional person with a reference sheet (front, profile and medium shot, and full body in the newest; some bring both profiles) and a voice in English, Spanish and Catalan, so it asks for no consent. Pick an item and add it to your open story with its pictures. Free includes about 10 avatars and 30 assets, and Creador the whole base. Premium items are bought once with credits and stay yours: Pro chooses 2 a month and Estudio has them all.
  - Example films by sector, each one to watch on its page, and in English, German or Catalan when it has that version.
  - Avatars, characters, settings and props, each type with its own filters.
  - Sorted for the story you have open: its format, style and language first.
  - A base in every plan; premium items for credits, yours for good.
- **Your own library**: Save any character, avatar, setting or prop of a story and use it again in the next one.
  «Save to library» on a card in Scenario, or on the cast of a shot in the storyboard, keeps a copy with its pictures, its reference photos, its voice and its description, even if you delete the story later. In the Library, the «Mine» tab lets you search it, order it, rename items and tag them, and «Add to the story» brings one into the story you have open, with its own copy of the files. The Library drawer in each step has it too. Only you see it, and a real person's photos are only saved by whoever confirmed their consent.
  - Save from the Scenario cards or the storyboard's cast.
  - Search, order, rename, tag and delete in «Mine».
  - A real person keeps the consent you confirmed; nobody else can take them.
- **A library for the whole team**: Share your characters, avatars, settings and props with your team, and use theirs.
  «Share with the team» on an item of your library puts a copy of it, with its own files, in the Library's «Team» tab, saying who shared it. Everyone in the team finds it there and in the Library drawer of each step, and adds it to the team's stories in one click. The owner and editors rename and remove items; reviewers only use them. Removing an item from the team leaves the original of whoever shared it, and a real person's character, shared only by whoever confirmed their consent, stays in the team's stories.
  - Share from «Mine»; everyone in the team uses it.
  - Owners and editors change it; reviewers only use it.
  - A real person stays in the team's stories.

## Shooting

Every shot with video, sound and camera, cheaply first.

- **Draft first, quality last**: Try each shot cheaply and pay for top quality only once.
  Each shot is first generated as a draft in Veo 3.1 Lite at 720p, the cheapest video. You approve it for free and, once you like it, finalize it once in Veo 3.1 Fast, Veo 3.1 or Gemini Omni Flash at 1080p, or, with the add-on of the models from other companies, in MiniMax, Kling, Wan or Seedance, which keep the characters' portraits, seeing the price before you confirm. The draft stays on screen until the final clip arrives. Each model sets how long a shot can be (Veo 3.1 up to 8 s, Gemini Omni Flash 15 s, Kling 15 s, Wan and Seedance 30 s), and the Pitch's slider follows the one you choose.
  - Drafts in Veo 3.1 Lite at 720p; approving costs nothing.
  - Final in Veo 3.1 Fast, Veo 3.1 or Gemini Omni Flash at 1080p, once per shot.
  - A filter shows only the shots still pending.
- **A camera for every shot**: Lens, angle, height, rig and focus per shot, and a shot list for the set.
  In Filmmaker mode each shot has its own camera: lens in millimetres, angle, height, rig and focus. The picture and the clip are made with it, and the shot list gathers every shot with its framing, camera, light and sound, ready to download as CSV. The camera also travels in the editing package and to Unreal and Unity. Each shot also has its own direction: lock it so «Generate all» leaves it alone, its length and model, the seed that keeps its look, what to avoid and the frame it ends on.
  - Lens, angle, height, rig and focus for each shot.
  - A shot list with framing, camera, light and sound, editable in place and downloadable as CSV.
  - The camera goes with the editing package and to the engines.
  - Each shot's direction: lock, length, model, seed, what to avoid and last frame.
- **A film crew of AI agents**: Director, producer, camera, sound, Unreal, Unity and more, at a production meeting you lead.
  In Filmmaker mode, the production office puts twenty AI agents on a studio floor, one for each role of a shoot: director, producer, screenwriter, assistant director, floor manager, script supervisor, camera, director of photography, gaffer, art, costume, acting coach, sound, music, voice-over, editor, colorist, VFX, and Unreal Engine and Unity experts. Give the crew an order and the director shares out the work: the agents speak one after another, answer each other, propose changes to your story, and the director decides what to apply, choosing one when two agents want to change the same thing. The script supervisor looks at the storyboard images, cut by cut, and once you apply the changes it can check that what the crew flagged is fixed. Or click an agent to give the order to them alone. Nothing changes until you apply it. Choose how to see it: Interactive mode, the studio floor with each proposal, or Real mode, a real film studio where Marta the director, Leo on camera and the rest talk to each other by name, every order is a dialogue you hear in their own voices, and you can give the order by speaking, or Virtual mode, a film studio building floor by floor (production, art, sound, post, the stage and the LED volume) where the crew act out every order: they talk, argue, worry and applaud, and the camera goes to whoever speaks. Before the first order it plays a real shooting day, from the call sheet to «Cut! That's the one».
  - Twenty roles of a real production, each checking what their craft checks.
  - A production meeting you watch: who speaks, who answers whom.
  - Proposals you apply with one click to every scene they concern, including each shot's camera, then see each scene before and after and keep or undo it.
  - Orders to the whole crew or to one agent, and a check once you apply.
  - Real mode: people with names and voices who talk like a real crew; give your orders aloud.
  - Virtual mode: the whole studio building, floor by floor, where the crew live every order as on a shooting day; a short video on this page shows them talking an order over.

## Editing and delivery

The cut, ready to publish or to finish elsewhere.

- **Looks shot, not generated**: Real skin and film grain: faces without the waxy look and a finish that looks like a shoot.
  In the realistic styles every image asks for skin with pores, fine lines and fine hair, never smoothed; characters' portraits are lit by a window rather than a studio; shots ask for a cinema lens with the depth of field each one needs and light from a source the place has; and each clip keeps the skin of its first frame as people move and turn. In the editor, «Finish» lays film grain, a soft vignette and a grade (Film, Warm, Cool or Black and white) over the whole movie, the same in the player, in the download, on social networks and in shared links, with the lower thirds and subtitles clean on top. «Real shoot» adds what a camera and a film do: a filmic curve, so the highlights fade instead of burning; the look of a digital cinema camera, a warm 500T film or a cold film; halation, the warm glow film gives strong lights; and less of the AI's crisp sharpness and waxy skin, under the grain. «Lens», «Camera in hand» and «Period», each on its own slider and never on by default, add a real objective's colour fringe and softer corners, the slight drift of a camera held by hand on still shots, and the dust, scratches and weave of old film for period pieces. «Recommended values» sets every slider to what looks most like real filmed footage for the colour and the camera chosen. New stories in a realistic style start with it on. A magnifier over each frame, each paused clip and each before and after shows skin, lips, hands and eyes at up to 4×, at full resolution, so you judge them before redrawing or filming.
  - Skin with pores and fine hair, never waxy, in images and clips.
  - Portraits lit by a window, shots with a cinema lens and motivated light.
  - Film grain, vignette and grade on sliders, with a before and after cut on your own frame, and «None» to turn it off.
  - «Real shoot»: filmic curve, camera or film emulation, halation and less artificial sharpness, each on its own slider, and a lens with a colour fringe and softer corners if you want it.
  - A camera in hand for still shots and, for period pieces, the dust, scratches and weave of old film.
  - The same finish in the player and in every export.
  - A magnifier at full resolution, on shots, characters and Library avatars, to check the skin before you redraw.
- **A check of the film before you deliver it**: It listens to the finished film and watches every shot, and tells you what to fix before your client sees it.
  «Check the film», in the editor's notices and in «Deliver», takes the finished MP4 and checks it as a quality-control supervisor would. It writes down the sound with Google's Chirp 3 and compares it, shot by shot, with each shot's narration: is the voice there, does it say the text, is it cut off before the end, is a voice heard that nobody wrote. It flags long silences, a film with no music and its loudness. With Gemini it watches each shot for black or empty pictures, garbled or misspelled text (the word on a bib that comes out wrong), logos nobody asked for, a character who doesn't look like their picture, and deformed hands. The report lists every problem by shot and minute, how serious it is and the button that fixes it: make the voice, make the music, go to the shot, redo the shot. The serious ones are also told when you create the review link for your client.
  - The narration shot by shot: is it there, does it say its text, is it cut off before the end.
  - Long silences, a film with no music, voices nobody wrote and the loudness.
  - Black or empty shots, garbled text, unwanted logos, a character who changed look and deformed hands.
  - Each problem with its shot, its minute, how serious it is and the button that fixes it.
  - You see the most it can cost before you start, and you pay only what it uses.
- **Ready to publish and to edit**: Full-screen review, formats for each network, YouTube, links and a package for your editing software.
  Review the cut in the editor and watch it full screen: the timeline shows each shot's storyboard picture at once and its frames as they arrive, and the next time you open the story your browser already has them. Each cut between scenes gets its transition, chosen for you or by you with a preview (seamless, dissolve, soft fade to black or white, wipe, push, zoom, J and L cuts), the same in the player and in every export. Export in MP4, MOV, WebM or HEVC, with versions for each social network, upload it straight to YouTube or share it with a link for WhatsApp and Telegram. If you carry on in your editing software, the editing package has each shot's clip and sound, the narration and music as WAV, and the edit as OpenTimelineIO, which DaVinci Resolve opens. «Suggest with AI» proposes the lower thirds the shots need, from their narration, and places them away from the speaker's face. Each shot's details say which model made its image and clip, when and with which settings.
  - Watch the cut full screen, on a timeline that opens at once, even on long stories.
  - Transitions between scenes, chosen for each cut and previewed in the player.
  - Versions for each social network, with subtitles in the picture, and upload to YouTube.
  - Links in Full HD to share in messaging apps.
  - An editing package with OpenTimelineIO and WAV tracks.
  - Every file marked as made with AI, and the EU «AI» label on the picture when the film needs it (EU AI Act).
- **Review and approval with your client**: Your client comments at the exact second of the film and approves it or asks for changes, without an account.
  «Ask for a review» under the editor's timeline makes a link to the current cut. Whoever gets it watches the film, pauses where they want to say something and comments: each comment knows its second and its shot. When they are done they press «Approve» or «Ask for changes», and you get an email with their note and comments. Back in the editor, the comments are tasks for each shot: press the time to jump to that moment, even if you have changed the timeline since, and mark each one done. When you change it, «New version» sends the new cut to the same link: your client compares it side by side with the one before and sees what was done. With the Agency add-on (79 € a month, on Pro or Estudio), each review goes under its client, with the minutes each one approved and a printable approval record.
  - Comments at the exact second, with the shot they fall on.
  - New versions in the same link, compared side by side, with what was asked in the one before.
  - «Approve» or «Ask for changes», with an email to you at once.
  - Tasks for each shot in the editor, to mark done one by one.
  - Your client types their name and email: no account and nothing to install.
- **Training videos for e-learning**: Training templates, a SCORM package for your platform and subtitles in any language.
  Pick a training template in the pitch (case study, good and bad practice, micro-lesson, conversation or presenter) and the script is built around what the learner must take away, ending with the key idea said out loud. Then export the film as a SCORM 1.2 or 2004 package that any e-learning platform (LMS) accepts: it brings its own player, the subtitles, and tells the platform when the learner started, where they left off and when they finished.
  - Five templates: case study, good and bad practice, micro-lesson, conversation and presenter, whose whole text you hear and approve before any video is made, with lips in time with it: Veo’s, lip sync or pro lip sync, each with its extra credits shown.
  - SCORM 1.2 and 2004: started, resume where they left off, completed at 95%.
  - Subtitles from the narration and the dialogue, translated into 37 languages (Catalan, Basque and Galician included), as SRT or WebVTT, or in the picture, and lower thirds in your brand colour, spelt exactly as you write them: names, key concepts, numbered steps, chapters, tips and warnings, with their typeface (easy-reading ones included), shape, transition and place; the AI proposes them from the narration and places them away from the speaker's face.
  - Video series from one sheet, with the Series add-on (€99 a month with 120 minutes of finished video included): you create and prepare your own series, invite your people, each with their role (scripts, review or production), and follow its step-by-step guide. Download the template from the series page and fill in one row per video (with its checks), or use a form; the videos are made in batches of 50 with the same presenter, voice, opening and closing with your logos, lower thirds and subtitles. Scripts can have scenes where characters talk to each other, each with their own voice and lips in time, and a shot lasts up to 16 s, cut only between sentences. You review each video next to its script, approve it or send single shots back, and only what you approve is delivered as MP4, SCORM and subtitles by ID. Everyone invited opens the series from «Series» on the rail and finds its videos there, by module, with a search through the scripts.
- **Versions for every audience**: The same film for another market, language, age or length, paying only for what changes.
  From a finished film, describe who the new version is for: another market or language, an age, a 6, 15 or 30 second cut, another call to action or product. The AI adapts the script and keeps every shot that still works; only what changes is made again. A version in another language is dubbed: narration and dialogue are translated, shots without dialogue are reused, and characters with a cloned voice keep it. In a presenter video, the presenter's shots are filmed again so the lips follow the new narration. In the editor, «Change language» dubs the film in one step, and the subtitles can be shown on the player in any language. To try your own variation, «Save a copy as…» copies the whole story under another name at no cost, and the original stays as it was.
  - Market, language, age, 6/15/30 s cuts, call to action and product.
  - Approved shots are reused; the storyboard lists only what to make again.
  - Dubbed versions, Catalan and Galician included, with the same narrator and the characters' cloned voices, straight from the editor with the price shown first.

## Virtual production

The story carries on in Unreal Engine, Unity and on LED walls.

- **Unreal Engine and Unity, connected**: Your story in Unreal Engine 5 and Unity 6, in sync both ways.
  With the plugins for Unreal Engine 5 and Unity 6, the story opens in the engine as a sequence of shots, with each clip, its sound, the script and reference panels of the characters and settings. What you render in the engine comes back to the app as the shot's clip or image. Both engines can work on the same story at once: the app keeps the one version and each engine syncs with it. With Estudio, or on Pro with the Plató virtual add-on (€99 a month).
  - Unreal: a Level Sequence with each shot's clip and sound, and reference panels.
  - Unity: a Timeline with the same tracks.
  - Change the order or length of shots anywhere, and the rest receive it.
  - Engine renders replace the shot's clip, and can be undone.
  - A step-by-step plugin guide inside the app.
  - Your LED plates play behind the subject in Unreal.
  - Gemini checks each Unreal shot against its storyboard.
  - The previs keeps the 180° rule, with shot and reverse shot.
  - A 3D set in the web: each shot's camera and the stand-ins, edited here or in Unreal, both ways.
  - Camera moves on a timeline like Sequencer's, synced with Unreal key by key.
  - Set recipes: a light that changes, fog, a dolly on a rail, a crane, something passing and a screen, placed in the web and built in Unreal.
  - Your Unreal level's Blueprints in the web: change their variables' values from either side.
  - Animated stand-ins: a path of keys and animations (walk, sit down, talk…) per shot, played on the timeline.
- **The previs in one click, and the engine in your own words**: The whole story's previs from its screenplay, orders in plain words, and your AI agent in Unreal.
  «Build the previs» reads the screenplay and lays out the whole story in the engine for free: a cinema camera per shot with its framing and the move its camera line asks for, cut over the Veo clips, the storyboard on boards, stand-ins for the cast and the story's light. Then fine-tune in your own words, in each engine's module or inside the engine: “a close-up of shot 3 with a slow tracking shot, at sunset, and render it”, and Gemini turns it into actions you review before they run. In Unreal Engine 5.8, an AI agent such as Claude Code connected to the editor gets the same tools, and agents connected to the app can queue them for any engine.
  - The whole story's previs in one click, free, in Unreal and Unity.
  - Cameras with framing and movement from one sentence.
  - Your AI agent directs Unreal 5.8 with the story's screenplay in hand.
  - Claude.ai, Claude Desktop and ChatGPT connect to your stories: sign in to Utopia, no token to copy.
  - A chat beside Unreal: run each order step by step and see where it changed.
  - Only actions from a closed list: no code ever runs on your computer.
- **Your AI assistants, connected to your stories**: ChatGPT, Claude, Cursor, Gemini CLI, VS Code or Codex work on your stories over MCP.
  Connect the AI assistant you already use to your account over MCP, the open protocol for AI tools. Claude.ai, Claude Desktop and ChatGPT just sign in to Utopia, with no token to copy. For Cursor, Claude Code, Gemini CLI, VS Code (Copilot), Codex CLI and Devin Desktop (Windsurf), create an access token in Settings → «AI assistants (MCP)» and copy the ready config; Cursor and VS Code install it with one click. The assistant then reads your stories or creates new ones, writes their characters, settings, props and shots, draws their pictures once you confirm the credits, brings back earlier versions, exports the movie, changes the edit, sends renders and queues orders for Unreal Engine or Unity. From the Pro plan; the orders to Unreal and Unity come with Estudio.
  - Claude.ai, Claude Desktop and ChatGPT: sign in to Utopia, no token to copy.
  - Ready configs for Cursor, Claude Code, Gemini CLI, VS Code, Codex CLI and Devin Desktop, with where each file goes.
  - The token never goes in the config: it stays in an environment variable.
  - Only your stories, and you disconnect an assistant or revoke a token whenever you want.
- **Backgrounds for LED walls**: Seamless looping backgrounds for virtual production sets.
  Make the looping background for a virtual production LED wall, such as the landscape passing by a car's side window. Pick a place or describe your own, the direction and the length (32 seconds to 2 minutes). The app first draws a keyframe every 8 seconds for you to review; then Veo makes each segment between two keyframes and your browser joins them into an MP4 that loops without a jump. Try it as a 720p draft and make the final in 4K.
  - Keyframes you review before any video is made.
  - A 720p draft to check the movement, and a 4K final for the wall.
  - An MP4 that loops with no visible seam.

## How you work

As guided or as detailed as you want, alone or as a team.

- **A screening room, not a control panel**: The picture and the main action in sight; the rest one click away, in a panel or with ⌘K.
  Utopia's interface is built like a screening room. A rail on the left takes you to your stories, a new story, the Library, the series and your team; the four steps run along the top as a strip of film. In each step you see the picture and the one action that moves the film forward: the storyboard shows big frames, the editor puts the player on top with a thin timeline always in sight, and the scenario shows your cast, places and props as pictures. Pick anything and everything about it opens in a panel beside it, from the camera of a shot to a client's comments. ⌘K opens, jumps and changes things by typing, and the same layout fits a 13-inch laptop and a phone.
  - A rail with your stories, the Library, the series and the team, and the steps as a strip of film.
  - Each step shows the picture and its main action; the rest opens in a panel beside it.
  - ⌘K to open a story, jump to a step or change the language, theme or mode by typing.
  - Made for a 13-inch laptop, with a bar at the bottom on a phone.
  - The one interface for everyone since 2 November 2026.
- **Three modes, one film**: Beginner, Professional or Filmmaker: as much control as you need.
  Beginner keeps it simple: from one message to a finished film, with the most efficient video model, at 720p. Professional adds control: the step-by-step form, the AI models, each scene's prompts, more export formats, LED backgrounds and teams. Filmmaker adds the tools of a shoot: each shot's camera, the shot list, the production office with its crew of AI agents, and Unreal Engine and Unity. A table compares the three, and every part of the app has an «i» that explains it, plus a quick-start guide.
  - Beginner, Professional and Filmmaker, switched in one click.
  - A table that compares what each mode can do.
  - An «i» on every element and a quick-start guide.
- **A studio that remembers you**: Your usual style, format, music and voice, and your people, in every new story.
  The app learns from what you do: the style, format, genre, music and narration voice you keep choosing, the people with a photo or cloned voice in your stories and the corrections you keep asking for. New stories start that way, and when a pitch names someone from your stories, you choose whether they keep their face and voice. You see, edit or delete each memory, or turn it off, in Settings.
  - Your usual style, format, film and music genre and narration voice.
  - Your recurring characters with their photos and cloned voice.
  - Corrections you repeat, passed on to the writer; you edit or delete everything.
- **It tells you when your film is ready**: Start the film and go: a notification or an email tells you when it's done, or if it needs you.
  Veo takes minutes per shot, and a whole film longer. Leave it working and carry on: when the videos, «Create all», an export or a link end and you aren't looking at the app, a notification in your browser and, after a while away, an email tell you, with a link straight to the story. It also tells you when a video couldn't be made or «Create all» stopped. With the app closed the videos still get made, and the notice still reaches you. With the app in front of you, nothing interrupts you. You choose each channel in Settings.
  - A browser notification and, after a while away, an email that opens the story.
  - It also tells you when a video fails or «Create all» stops, so nothing waits for nothing.
  - It works with the app closed, and you turn each channel on or off in Settings.
- **A help assistant that knows the app**: Ask how to do anything, or how to make your film better, in your own words.
  Not sure where something is or why a shot came out wrong? Ask the help assistant as you would ask a colleague, in English, Spanish or Catalan. It answers from the app's own guides and questions, knows which mode and plan you are on, says when something needs another one, and opens the right screen with one click. It's always at hand: the clapperboard in the bottom right corner of every screen.
  - Answers grounded in the app's guides, never invented.
  - Takes your mode and plan into account.
  - Opens the screen or window it talks about.
  - With a story open, it makes the clips or redraws a shot for you, saying the cost before spending anything.
  - With a support package, «Talk to the team» opens a request with your question, and the team's answers reach you in «My requests» and by email.
  - A two-minute guided video of the whole process, in your language (Help → Watch the intro video), and a short one inside the production office.
  - On the 1st of each month, an email with the last month's news in the app, in your language; one click turns it off.
- **Plans that say what you can make**: Four plans with monthly credits, each showing the minutes of film and stories it makes.
  Free, Creador, Pro and Estudio give credits every month, and each plan shows what they make: minutes of film as a draft, in final quality, in top quality or in 4K, plus example stories. Images, video, voice, music and text draw from the same balance, each action shows its price before you confirm it, and if a generation fails the credits come back. From Creador, a finished minute has a cap: if a film costs more, the difference comes back when you export it or your client approves it, and a final clip with a technical defect is made again for free, once per shot. Creador, Pro and Estudio start with a free trial of 18 days, once per person: you give your card, nothing is charged until the day shown before you confirm, you get an email 3 days before, and you cancel in one click. The trial comes with 3,000 credits and video at up to 1080p; the plan's credits and 4K arrive with the first payment. If you run out, on any plan you can buy usage credits to keep making videos, which never expire. For a single project there are 30-day passes, with no subscription: Pro for €199 and Estudio for €799. Founder price: 30 % off the first year of a yearly plan if you subscribe by 31 January 2027. Every price in credits shows what it's worth in euros on your plan. The models from other companies (not Google), «Create in 3D» and adult mode come in an add-on for the paid plans: one payment of €29 with 3,200 usage credits, and they're paid with usage credits. Launch offer: the paid plans give twice the credits until 18 December 2026 (the extra ones not used by then expire that day), and clips asked for in Veo 3.1 Fast are made with Veo 3.1, the top model, for the same credits. An automatic top-up can buy usage credits with your saved card when you run low, up to a monthly cap you set.
  - Try any paid plan free for 18 days, and cancel in one click.
  - Twice the credits on the paid plans until 18 December 2026.
  - Each plan in minutes of film and stories, by quality.
  - Choose a plan below: once you sign in, you pay for it on Utopia's own payment page, with Stripe.
  - If something fails, the credits come back on their own.
  - Support from the team on top of any plan, by request from the help chat: Basic (answer within 2 working days, €19 a month, included in Estudio) or Premium (priority within 8 working hours and a named person, €129 a month), followed and answered in «My requests».
  - Run out? Buy usage credits on any plan: €100, €250, €1,000 or €5,000, saving 10, 20, 30 or 33 %, and they never expire.
  - Invite someone with your link: when they pay their first month, you both get usage credits (3,000 with Creador and up to 35,000 with Estudio).
  - Automatic top-up with a monthly cap, and invoices with your company's legal name, tax ID and address, each with its PDF.
  - Discount codes at checkout, and 30 % off for 12 months for education and non-profits.
  - Loyalty gifts at 6 and 12 months, and your shared films invite in your name.
  - 25,000 free credits when you join during the beta.
- **Teamwork**: A team space with shared stories and a common wallet.
  Create a team and invite your people by email. In the team's space, new stories belong to every member and the AI is charged to the common wallet, which the owner manages. A story you started alone in your personal space can join the team too, with everything it has, and you can take it back. You can belong to several teams at once, and switch between your personal space and each team's from the rail, in Account. Creador teams take up to 3 people, Pro up to 5, or 10 paying €15 a month for each one more, and Estudio up to 10, with €8 a month for each one more. Review links take unlimited reviewers, free. From the team window you can also set up a Google Meet with every member invited, and bring photos and files into any story straight from Google Drive. Companies accept the data processing agreement (GDPR, art. 28) in the app and download a copy. Inside the team, the owner can also add up to 10 reviewers with an account, who take no seat and only comment and approve, and set each member a monthly limit of credits.
  - Invitations by email.
  - Stories shared within the team, even ones you started alone.
  - A common wallet for the whole team.
  - Belong to several teams and choose where you work.
  - A data processing agreement (GDPR) for companies, accepted in the app.
- **Your stories, in order**: Copy, rename, pin, archive and sort your stories, and share one with your team.
  Your Stories keeps every production at hand. Save a copy of a story under a new name to try another ending, with its cast, storyboard, clips, voices, music and lower thirds, at no credit cost. Rename it with a double click, pin the ones you're working on to the top, archive the finished ones and sort by last edit, creation or name. Its details say when it was made, how many shots it has, how long it runs and how much space it takes. And with «Share with the team», a story you started alone joins your team with everything it has.
  - «Save a copy as…» with everything in it, without spending credits.
  - Rename, pin to the top, archive and bring back.
  - Sorted by last edit, creation or name, with each story's details.
  - Share a personal story with your team, and take it back.

## Use cases

- [Training videos](https://app.utopiadreams-vfx.com/casos/videos-de-formacion?lang=en): Dramatised cases, a presenter and whole series to train your staff, with SCORM and subtitles.
- [E-learning and SCORM](https://app.utopiadreams-vfx.com/casos/e-learning?lang=en): Micro-lessons and whole courses for your platform, with SCORM 1.2 or 2004 and subtitles.
- [Adverts](https://app.utopiadreams-vfx.com/casos/anuncios?lang=en): TV spots and social ads with a story, in every format, length and language.
- [Product videos](https://app.utopiadreams-vfx.com/casos/video-de-producto?lang=en): Your product in use, in settings you couldn't film, for your online shop and your social media.
- [Virtual production](https://app.utopiadreams-vfx.com/casos/produccion-virtual?lang=en): The previs of the whole story in Unreal and Unity, and looping backgrounds for LED stages.
- [Comparison](https://app.utopiadreams-vfx.com/alternativas?lang=en): What Utopia does next to Google Flow, Runway, Synthesia, HeyGen and LTX Studio, and when each one suits you.

## Frequently asked questions

### What is Utopia Dreams Platform?

An AI film studio in the browser. From an idea or your own screenplay it writes the story, creates characters, settings and props, draws the storyboard, generates every shot with video and sound, narrates, scores and edits it, ready to export, publish on social networks or carry on in Unreal Engine and Unity. It is made by Utopia Dreams VFX, Raúl Bellmunt Tabero's studio in Terrassa (Barcelona, Spain), a member of the Google for Startups Cloud Program. It is in beta: you request access and the team approves it.

### How do you make a film with AI in Utopia?

1) Write a pitch or import your screenplay. 2) The app writes the story and creates the cast, settings and props with images. 3) It draws the storyboard shot by shot. 4) It films each shot with video and sound, first as a cheap draft, then in final quality. 5) Add narration, dialogue with fixed or cloned voices, music and lower thirds. 6) Edit, give it a film finish (grain, vignette and colour, at no credit cost) and export as MP4, for social networks, as SCORM or to a game engine.

### How is it different from other AI video generators?

Video generators make loose clips and avatar platforms make a talking head. Utopia carries the whole film: script, a cast that keeps its face in every shot, storyboard, shots with camera and sound, dubbing into other languages with the same picture, editing, SCORM packages for training, previs in Unreal Engine and Unity and backgrounds for virtual production LED volumes.

### Is it an alternative to Google Flow, Runway, Synthesia or HeyGen?

It does a different part of the job. Google Flow and Runway generate and string together AI video shots; Synthesia and HeyGen make videos with an avatar talking to camera. Utopia uses video models such as Veo, the one behind Google Flow, and builds the whole film around them: script, a cast with the same face in every shot, storyboard, shots with sound, narration, music, editing and delivery as MP4, as SCORM or to Unreal Engine and Unity. If you only need a single clip or a presenter reading a text, those tools are more direct; if you need a piece with a story, several characters and an edit, Utopia saves you moving from one to another.

### What kind of projects is it for?

Any audiovisual piece with a story: ads and brand videos in several formats and languages; training videos with a presenter, subtitles and a SCORM package, also in batches with the Series add-on; short films and fiction; storyboards and previs to prepare a live-action shoot, which carries on in Unreal Engine or Unity; and backgrounds for LED virtual production stages. There is a Beginner mode for newcomers, and a Filmmaker mode and team spaces for production companies.

### How does it keep the same faces, clothes and voices in every shot?

Each character's photo is the identity reference in every image and shot, and a fixed or cloned voice says their lines. On top of that, the coherence advisor checks each step against the continuity rules (photos, voices, clothes, faces in the first frame, camera, light), says how to fix each warning and fixes what it can in one click, before the clips are paid for. Its rule checks use no credits.

### Which languages does it work in?

The interface is in English, Spanish and Catalan. Stories, voices and subtitles can be made in more than 30 languages, Catalan, Galician and Basque included, with Antton, a native Basque narrator, on the Pro and Estudio plans. A film can be dubbed into another language keeping the picture.

### Can I use Utopia from ChatGPT, Claude or another AI assistant?

Yes, over MCP, the open protocol for AI tools. Claude.ai, Claude Desktop and ChatGPT connect by signing in to Utopia; Cursor, Claude Code, Gemini CLI, VS Code, Codex CLI and Devin Desktop use an access token from Settings → «AI assistants (MCP)». The assistant can read your stories, create new ones, write their characters, settings, props and shots, draw their pictures (it tells you the credits first), bring back an earlier version, export the movie, change the edit and send orders to Unreal Engine or Unity. It comes with the Estudio plan.

### How much does it cost?

There is a free plan with 300 credits a month and three paid plans: Creador (€49 a month), Pro (€149 a month) and Estudio (€599 a month), which make about 2.2, 7 and 28.2 minutes of finished film a month, 17 % off when paid yearly. Each paid plan starts with a free trial of 18 days, once per person, which you can cancel in one click before the first charge. Usage credits that never expire can also be bought, and the models from other companies (not Google) come in an add-on for the paid plans, one payment of €29. Each AI call spends credits by model and quality, and drafts cost far less than the final take. Prices without VAT.

### Can I try it for free?

Yes. The Free plan gives credits every month without a card, enough to try a draft, and each paid plan starts with a free trial you can cancel before the first charge. During the beta, access is by request: ask for it on this page and an administrator approves it.

### What is a credit and how far does it go?

Each AI call (text, image, video, voice or music) spends credits by model and quality. You first film each shot as a cheap draft and only make the final take of the shots you approve. The plan cards show how many minutes of film and how many ads, shorts or training videos each plan makes.

### Can I get help from the Utopia team?

Yes. The help assistant (Help → Ask for help) answers in the app at any time, and with a support package you open a request to the team from the same chat and follow it in «My requests». On top of any plan, Free included, you can add Basic (€19 a month, first answer within 2 working days, help with your account and invoices, video guides) or Premium (€129 a month, priority requests answered within 8 working hours, a named person on the team, a monthly written review of your stories and help with Unreal Engine, Unity and LED walls). Support is by request only, not by phone, and response times are targets, not guarantees.

### Which AI models does Utopia use?

Google's latest models on Vertex AI: Gemini for the script and the assistants, Nano Banana for the images of characters, settings and storyboard, Veo 3.1 for video with sound, Lyria for music and Gemini Text-to-Speech for voices. Stories in Basque can be narrated by Antton, HiTZ's open Basque voice, which runs on Utopia's own servers. With an add-on, the paid plans also get video and 3D models from other companies: MiniMax, Kling, Wan, Seedance, Hunyuan3D, Trellis and Tripo. The AI models page lists each one and what it is best at.

### Can I choose the model and the quality?

Yes. Beginner mode picks the most efficient models for you; Professional and Filmmaker let you choose each one, from Veo 3.1 Lite for drafts to Veo 3.1 for the best take, in 720p, 1080p or 4K, or, with the add-on, another company's video model, and the app tells you the credits before you spend them.

### Who owns the films I make?

You do. What you upload or write is yours and, as far as the law allows, so is what the app generates for you, commercial use included. AI models may produce similar results for other people, and generated content may not be protected by copyright in every country.

### Is my content used to train AI models?

No. Your content is only stored and processed to provide the app. Google's models run on Google Cloud's Vertex AI, whose terms don't let Google use it to train its models, and open models such as the Basque narrator run on our own servers. The other companies' video and 3D models and Sync Labs' lip sync run on fal.ai only when you use them, and never if you choose «Google models only» or «Data in the EU». The privacy policy lists every provider and what each one receives.

### Is AI-generated content labelled?

Yes, as article 50 of the EU AI Act requires: every movie and soundtrack you export says in its metadata (IPTC standard) that it was made with AI, the images, clips, music and voices from Google's models carry Google's invisible SynthID watermark, and shared films, YouTube descriptions and social posts say so too. You can also put the EU's «AI» label on the picture when you export.

### What do I have to do under the AI Act when I publish?

If you publish for your work or business, you tell your audience it's AI. A film with realistic people, places or events (an advert, a training or informative video) needs the «AI» label where viewers see it: in the editor, Export → «AI» label on the picture → The whole film. In an obvious work of fiction, the start or a mention in the credits or the description is enough. Don't remove the marks from the files, and label AI-written text that informs the public on matters of public interest unless a person has reviewed it.

### Does it work with Unreal Engine and Unity?

Yes. The Unreal plugin and the Unity package open the story with its shots, cameras, characters and sound, and changes come back to the app. It also makes backgrounds for virtual production LED volumes.

### Can it make backgrounds for LED walls?

Yes. It makes seamless looping backgrounds for virtual production LED volumes: you first review a keyframe every 8 seconds, then Veo films each segment and your browser joins them into an MP4 that loops without a jump, as a 720p draft or a 4K final.

### Is it good for training and e-learning videos?

Yes. It has training templates (case study, good and bad practice, micro-lesson, presenter to camera), a lip-synced presenter, lower thirds, subtitles in several languages and SCORM 1.2 and 2004 export with a transcript, ready for any learning platform (LMS). A scene with long dialogue can be one continuous shot of up to 40 s, with every word said in the characters' voices. It also produces series of videos in batches from a spreadsheet.

### Can my team work on the same films?

Yes. A team shares its stories and a common wallet of credits that the owner manages. Invite people by email, bring a story you started alone into the team, and set up a Google Meet with everyone from the team window. Each paid plan says how many people its team takes.

### Can you produce a long series for my company?

Yes. With the Series add-on, shown next to the plans, you create your own series and invite your people: download the template from the series page and fill in one row per video, and the Utopia team prepares the production and makes it in batches with the same presenter, voice, opening and closing. Scripts can have scenes where characters talk to each other, and a shot lasts up to 16 s, cut only between sentences. In a review queue you approve each video before it is delivered as MP4, SCORM and subtitles. For a large series, write to hello@utopiadreams-vfx.com.

## Latest posts

- [Com fer una pel·lícula amb IA el 2026, pas a pas](https://app.utopiadreams-vfx.com/blog/como-fer-una-pellicula-amb-ia-pas-a-pas) (2026-11-02)
- [Cómo hacer una película con IA en 2026, paso a paso](https://app.utopiadreams-vfx.com/blog/como-hacer-una-pelicula-con-ia-paso-a-paso) (2026-11-02)
- [Vídeos de formación con IA y FUNDAE: qué dice la guía de costes del material didáctico](https://app.utopiadreams-vfx.com/blog/videos-de-formacion-con-ia-fundae-material-didactico) (2026-11-02)
- [Google Flow suma fotogramas de inicio y fin y exporta en 4K](https://app.utopiadreams-vfx.com/blog/flow-gemini-omni-fotogramas-inicio-fin-4k) (2026-10-29)
- [Veo 3.1 Lite: el vídeo con IA de Google, a menos de la mitad de precio](https://app.utopiadreams-vfx.com/blog/veo-3-1-lite-video-ia-mas-barato) (2026-10-29)
- [Kling 3.0: clips de 15 segundos con audio nativo en varios idiomas](https://app.utopiadreams-vfx.com/blog/kling-3-0-audio-nativo-15-segundos) (2026-10-29)
- [Netflix compra InterPositive, la empresa de IA para cine de Ben Affleck](https://app.utopiadreams-vfx.com/blog/netflix-compra-interpositive-ia-postproduccion) (2026-10-29)
- [Synthesia levanta 200 millones para la formación con vídeo e IA](https://app.utopiadreams-vfx.com/blog/synthesia-200-millones-formacion-con-video-ia) (2026-10-29)
- [Fondos generados con IA en un plató LED, escalados a 15K](https://app.utopiadreams-vfx.com/blog/fondos-generativos-en-pantallas-led-produccion-virtual) (2026-10-29)

## Links

- [Utopia Dreams Platform](https://app.utopiadreams-vfx.com/sign-in?lang=en)
- [About](https://app.utopiadreams-vfx.com/about?lang=en)
- [Story guide and FAQ](https://app.utopiadreams-vfx.com/story-guide?lang=en)
- [Privacy](https://app.utopiadreams-vfx.com/privacy?lang=en)
- [Terms](https://app.utopiadreams-vfx.com/terms?lang=en)
- [Data processing (DPA)](https://app.utopiadreams-vfx.com/dpa?lang=en)
- [For companies](https://app.utopiadreams-vfx.com/empresas?lang=en)
- [Use cases](https://app.utopiadreams-vfx.com/casos?lang=en)
- [Comparison](https://app.utopiadreams-vfx.com/alternativas?lang=en)
- [AI models](https://app.utopiadreams-vfx.com/modelos?lang=en)
- [Careers](https://app.utopiadreams-vfx.com/careers?lang=en)
- [Blog](https://app.utopiadreams-vfx.com/blog?lang=en) · [RSS](https://app.utopiadreams-vfx.com/blog/rss.xml)
- [llms-full.txt](https://app.utopiadreams-vfx.com/llms-full.txt)
- [ard.json](https://app.utopiadreams-vfx.com/.well-known/ard.json): MCP / A2A