Hand over a document, and you get a training video for your employees. A voice reads the text, graphics and screen recordings of your own systems show the process, and an avatar can speak on screen if you like. We show you the script before the video is made. When a process changes, the video is generated again from the changed document.

In use

The production line behind it runs in-house and has produced slides, narration, photos and avatar videos for real modules, plus two complete promotional videos.

The Agentic Part

An agent writes the script from your document, scene by scene, and puts it in front of you. It then adds the narration and leaves a pause after every figure and every duration so it lands. Under each spoken passage it places a fitting picture: a diagram, a screen recording or a graphic card, and it varies the picture types so the video stays varied. The cut follows the narration. If you want a presenter on screen, you get an avatar, a generated presenter who speaks the text. When the process changes, the agent generates the video again from the changed document.

Main Features

You see the script before the video is made
A voice reads the text, with pauses after figures and durations
Diagrams, graphic cards and screen recordings of your own systems sit under every spoken passage
The cut follows the narration, and every picture fits the spoken text
The picture types change so the video stays varied
If you like, an avatar speaks as presenter on screen
When a process changes, the video is generated again from the changed document

Use Cases

A process in your company changes. You adjust the document, and the video is generated again from it.
New employees get to know a system. The video shows screen recordings of your system with narration, step by step.
You want a presenter on screen. An avatar speaks the text.