Hour One Video

Hour One Debuts Generative AI ‘Video Wizard’ for Turning Text Prompts into Finished Videos

Virtual being and synthetic media startup Hour One has introduced a generative AI tool for producing videos from a written description called Video Wizard. Hour One describes Video Wizard as a ‘prompt-to-video’ feature augmenting the Script Wizard introduced in January that uses OpenAI’s generative AI models to compose scripts.

Video Wizard

Video Wizard starts with writing a script from the text prompt but continues into video production by casting one of Hour One’s virtual humans to host and perform the script accompanied by images and sounds curated by Video Wizard. The result is formatted by the AI to an appropriate layout template which the user can then tweak or send back if they’d rather try again with a new prompt.

“Prompt-to-video with Video Wizard takes all the work out of video creation, and helps people who typically don’t think of themselves as creative to suddenly be so,” Hour One CEO Oren Aharon said. “For the first time, we present a new frictionless way to generate video and are pleased to take this important step in our mission to make studio-quality video creation available to everyone.”

Magic Media

As with Script Wizard, Video Wizard users can edit the script, rewording or changing its length, switch it to a first-person perspective, and play with tone options. Video Wizard points to Hour One’s larger strategy for its AI tools. The new generative AI features enhance what began as a way to make virtual receptionists for buildings before growing into producing synthetic news reports with AI anchors, among other uses. There are a growing number of video production platforms embedding generative AI tools in recent months. Adobe recently began adding video production features to its Firefly generative AI toolset with functions including AI-assisted editing and storyboarding. Meta has also dipped its toes in the same pool with its new Segment Anything Model (SAM), capable of dividing both images and videos into their component objects without training. SAM can identify and extract those objects within an image or video. And Adobe’s video tools are similar to Canva’s recent approach in providing extensive generative AI assistance for creative presentations and campaigns.


10 Minutes On Text-to-Video and GPT-3 with Arnon Kahani of Hour One

Hour One Adds GPT-3 ‘Script Wizard’ Writing Assistant to AI Video Editor

Hour One Debuts Synthetic Video News With Virtual Human News Anchors