YouTube has introduced a new feature that allows users to create a photorealistic AI avatar of themselves for use in Shorts. Abner Li reports for 9to5Google that the tool captures both a user’s appearance and voice to generate personalised video clips.
To set up the avatar, users record a live selfie and read a few prompts aloud within the YouTube app or the YouTube Create app. This one-time setup process can be updated at any time. Each AI-generated clip can be up to eight seconds long, and users can string multiple clips together.
YouTube states that “the avatar feature gives users an easier way to include themselves safely and securely in videos.” The selfie footage and voice recording are used exclusively for avatar creation. No other user can create content using someone else’s avatar.
Users can delete their avatar at any time. YouTube automatically removes it after three years of inactivity. However, existing videos featuring the avatar remain online unless the individual clips are deleted.
All avatar-generated videos carry watermarks and digital labels, including SynthID and C2PA markers, along with disclosures identifying the content as AI-generated.
To access the feature, users open the Create menu in the YouTube app and select “Make a video with my avatar.” The feature is rolling out globally, excluding Europe, for users aged 18 and older who own an existing YouTube channel.
Stay up to date
AI for content creation: the latest tools, tips and trends. Every two weeks in your inbox:
