Paste your script. Get a finished video.

No. Vid Optimus has no credits. You connect your own API keys for the AI providers you want to use. The built-in voice and stock photos and videos are free, with no key needed. Your licence is one flat price with unlimited videos.

No. You bring the script. AI Director plans the shots and visuals around your words, and your narration is never rewritten.

Yes. On the Script screen, choose Use a voiceover and pick your audio file (MP3, WAV, M4A, AAC, OGG, FLAC, Opus or WMA). It is transcribed with Groq or OpenAI using your own key, and you can fix any misheard word. Then it is cut into scenes that match your recording, and visuals and captions are built around it. Your recording is what plays, so no AI voice is generated.

Both. There is a download for Windows 10/11 and a separate download for macOS.

One at a time. To switch computers, deactivate the old one from your dashboard and activate the new one. You can do this any time.

Yes. Turn on consistent characters in the new-project wizard or on the Visuals screen. AI Director finds the people in your script and adds them to your cast with a description of how they look, and on Runware and the Vidoptimus Image Server each gets a reference portrait that goes with every shot they are in, so their face stays the same.

The whole story. With Story continuity on (the default), the Director reads your whole script once and writes a Story Bible: what the story is, its look, its places, its people and how it divides into stretches of place, time and mood. Each place gets a fixed description added to every picture set there, so it looks the same every time it appears. You can read and edit the Story Bible on the Plan screen. It only shapes the pictures; your words are never changed.

Yes. Text on picture lays a heading straight onto a scene's own picture in one of eight styles: Headline, Chapter title, Place stamp, Name tag, Quote, Split screen, Big number or Boxed headline. Photo treatments show a picture as a real object, like a polaroid, a newspaper clipping or an evidence board. Every word on them must be one your narration says, and AI Director can place them for you, including chapter titles, time jumps, re-hooks and name tags where the story turns.

Yes. New in 3.0, Doodle Maker turns a script or a recording into a video a hand draws on a board as it is spoken: pictures sketched and coloured in, words written letter by letter, and icons, arrows and charts drawn on the word they are said. It has its own place in the sidebar, 11 boards, and you see every board before any picture is made.

Yes. Every export also saves an .srt beside the MP4, and the Subtitles button saves one without rendering anything.

Every picture, video, voice, music file and layer is checked before rendering starts. If one is missing, the export stops straight away and lists it with its scene and shot, before a video is counted. Text cards, hooks and photo treatments whose files were lost are drawn again by themselves.

Yes. The new-project wizard has six templates: Documentary, History, Mystery, Top 10, Shorts explainer and News explainer. One pick sets up the whole edit the way that kind of video is cut, from the cut rhythm and graphics to the colour look and headline type, and every choice can be switched off. Top 10 works for ranked lists of any length, with each entry's own number and name on its first picture, and a Mystery keeps its answer for the moment it is revealed.

Yes. Turn on Charts, Maps or Motion graphics in AI Director. When a line says a number, names a place or makes a key point, it can show it as an animated chart, a moving map or a text card. There are 12 map types in five styles, and a route can carry a plane, ship, car or train. Chart values and map figures are only taken from what your script actually says, and places are looked up in map data built into the app. These are drawn on your computer, so they need no API key and cost nothing extra.

Yes. Tick Opening hook in AI Director and your video opens with a line from your own narration, slammed on screen with a punch-in, a flash and its own sound. The hook plays for four seconds before scene 1, with no narration or music under it, so scene 1 keeps its own first picture. There are 11 styles, from Statement and Number to Cold open, Countdown and Rapid fire. It only ever shows words your script says, and you can change or remove it on the Visuals screen.

Yes, with SceneSync. Choose your audio, add your images (JPG or PNG) and video clips (MP4) named in order, like 01.jpg, 02.mp4, 03.png, mixed however you like, and SceneSync lines them up. Images can get a slow zoom, and clips play as they were shot. Auto Split changes picture in the speaker's pauses, Exact Match starts each picture at a time you set, Transcribe & Guide tells you what pictures to make for each scene, and Beat Sync cuts on the beat of a song. Captions come from a Groq or OpenAI key; Beat Sync needs no key. The video then opens on the normal timeline.

Yes. Pick one of eight colour looks, from Cinematic and Warm documentary to Cold thriller, Vintage film, Black & white, Punchy, Noir and Faded matte, and set its strength. You can add film grain, a vignette and 2.39:1 cinema bars on 16:9 videos. The look grades your photos and clips only, so maps, charts, text cards and the hook keep their own colours, and captions stay sharp on top.

Yes. Run the Vidoptimus Image Server on a computer with a modern graphics card and it makes images with FLUX.2, in about 3 to 6 seconds each, with no per-image fee. Paste the Server URL and API key it shows into Settings, under AI Images. It reads reference pictures too, so your style and recurring characters keep their look. It is included with your licence: download it from the Image Server page, linked under Resources.

Yes. Music dips under your voice automatically and comes back in the pauses, and the finished mix is set to -14 LUFS, the loudness YouTube and TikTok play at. You can turn the levelling off, and set how far the music dips.

Captions are matched word for word to your script, not to raw speech-to-text. So they stay correct even if the transcription mishears a word.

Yes. Right-to-left scripts are laid out the way they read, in captions and in text cards, including word-by-word highlighting. Vid Optimus works it out from your own script, so there is nothing to switch on, and you can still set the direction by hand on any caption or text layer.

Six libraries, searched together: Pexels and Pixabay, plus NASA, Wikimedia Commons, Openverse and the Internet Archive. Only Pexels and Pixabay ask for a key, so stock search works the day you install. The licence and the credit line for everything you use are kept with your project and handed to you on the export screen.

A frame-accurate MP4, in 9:16 (vertical, for Shorts and Reels) or 16:9 (horizontal, for YouTube), from the same project.

Only during the free trial, which allows up to 5,000 characters per video. Paid plans have no script length limit.

The trial gives you 7 days, up to 3 videos a day, scripts up to 5,000 characters and no watermark. When it ends, the app locks until you activate a licence. There is no free plan after the trial.

Yes. AI images, stock search, voiceover and transcription all use online providers, and your licence is checked online. The final video is rendered on your own computer.

Windows 10/11 or macOS, plus disk space for your projects (you can pick any drive). You don't need a GPU. Vid Optimus finds the fastest video encoder on your computer and falls back to your CPU if there isn't one.

Please try every feature free for 7 days first. Once your licence is activated on a computer, all sales are final.

You do, including for commercial use. Images, clips and voices from third-party providers still follow those providers' own terms, so check them before publishing at commercial scale.