Built to be plain about video.

A video from a sentence is a promise that has to be broken into steps to keep. A model makes a few seconds at a time, so a longer video needs a chain: make a clip, take its last frame, start the next clip on it, and stitch the clips together.

That is what Viddio does. You describe a scene, pick a model, a shape and a length, and press Make video. The video is made clip by clip, every clip starting on the last frame of the clip before it, so it can run for minutes without a visible seam, and the clips are stitched into one file. Start the first clip on a picture of your own, or from words alone; end any clip on another picture; reorder, duplicate, remake or cut clips on a timeline.

What it is, and what it is not#

Today the default models are Previews, simulated in your browser: they paint clips from your prompt and a seed, and they honour your start and end pictures exactly, because frame 0 is your picture. They are not video models. Two real video models, Google's Veo and Kling, are connected in code and work only where their keys are set. Viddio is a library and a maker, in that order: Making videos comes with every plan, and so does the library.

Who makes it#

AVS Media, a small company in Nijmegen, the Netherlands. The imprint has the details. We say what is live, what depends on your setup and what is not offered, and the examples on this site use sample data.