At its Made on YouTube live event on Tuesday, the company unveiled new generative AI tools for Shorts creators. YouTube is bringing a custom version of Google’s text-to-video generative AI model, Veo 3, to Shorts, along with a new remixing tool, an “Edit with AI” feature, and more.
The custom version of Veo 3, called Veo 3 Fast, generates outputs with lower latency at 480p, making it easy to create video clips, YouTube says. And now users can do so with sound for the first time.
This update is rolling out in the United States, the United Kingdom, Canada, Australia, and New Zealand. YouTube plans to expand its functionality to more regions in the future.
YouTube is also bringing new Veo capabilities to Shorts, including the ability to apply motion from a video to an image. For example, you could animate a still image by making the person in it do a dance from a video. The company says this is possible through technology that captures and transfers movement from one subject to another.
Creators can now also use Veo to apply different styles to their videos, such as pop art or origami. Plus, creators now have the ability to add objects like characters or props with text descriptions.
These new capabilities will roll out in the coming months.
As for the new remixing tool, creators can turn the dialogue from eligible videos into catchy soundtracks for other Shorts.
“As the world’s largest creative playground, YouTube is where trends are born and where you can draw inspiration from. Imagine hearing a line of dialogue that sparks an idea — a funny phrase, a memorable quote, or a one-of-a-kind sound — and you want to remix it into a new sound,” YouTube’s Director of Product, Shorts and Generative AI Creation, Dina Berrada, wrote in a blog post. “With our new Speech to Song remixing tool, you’ll be able to do just that.”
YouTube notes that the feature uses Google’s AI music model Lyria 2 to create the soundtrack. Creators will be able to add their own vibe to the song, like “chill,” “danceable,” or “fun.”
The company plans to test this feature soon, it says, and will roll it out to more creators in the United States in the coming weeks.
With the new Edit with AI feature, creators can turn their raw footage into first drafts. It transforms raw camera roll footage into a first draft by finding and arranging the best moments and adding music and transitions. It can even add a voice-over that can react to what’s happening in the video, in either English or Hindi. The idea behind the feature is to give creators a starting point for their Shorts, YouTube says.
YouTube is experimenting with Edit with AI on Shorts and in the YouTube Create app and will expand the feature in the coming weeks in select markets.
Source: https://techcrunch.com/