Redakcja Choose TV
YouTube is taking AI to the next level and allowing users to create photorealistic avatars that look and speak exactly like them. The new feature is rolling out to Shorts and lets you record videos without actually appearing in front of the camera. You just need to make a short recording of your face and voice, and the system will generate a digital version of you that can then be used in clips. This builds on earlier AI tools from Google, but now adds the key element of a realistic voice.
Creating an avatar is easy but the effect increasingly resembles a real person
The process is straightforward; you record a selfie video and read a few sentences, and the system builds your avatar. Then you can generate short clips of up to 8 seconds that can be combined into longer materials. The most important thing is that the avatar maintains a consistent look and voice, making it start to resemble a real person rather than a typical animation. This can be a huge relief for creators who don’t want to record themselves but still want to be "present" in their materials.
YouTube secures the feature but still opens the door to a new kind of content
The platform is introducing security measures for avatars which will have AI markings (e.g. SynthID), and only the account owner has access to create them. Nevertheless, the change is massive, as creating content no longer requires a camera, lighting, or even being present in front of a screen. This could speed up the production of Shorts and change the way people build their online presence, especially in short formats.
YouTube is heading towards a future where you don't need to record yourself, just your digital counterpart. It's convenient, but also a bit unsettling.
source: 9to5google
