.jpg "Review: Clear Drop Soft Plastic Compactor (SPC)")
Gemini avatar features could soon let you place a digital version of yourself into AI-generated images and videos without picking up your camera. A recent Google app build points to tools that scan your face and turn it into a reusable 3D model inside Gemini, as seen in Android Authority’s APK breakdown.
The concept builds on Android XR’s earlier Likeness system, which created a realistic stand-in for video calls. Now it’s moving beyond headsets. The same approach is showing up inside Gemini, with signs it could work on phones and desktop browsers.
Instead of taking a new selfie every time, you would create a persistent version of yourself once and reuse it across different outputs. That shift favors speed, but it also helps keep your appearance consistent if you generate content often.
Apple already offers Memoji, a stylized version of you for messages and FaceTime. Google’s take looks more grounded in realism and designed to work directly inside generative tools, not just as a communication feature.
How the Gemini avatar works
The system appears to rely on a straightforward capture process. You record a short video of your face, and the app converts it into a 3D model. It follows the same basic idea as Likeness, just without requiring a headset.
On-screen prompts guide you to frame your face and capture enough detail. Once completed, the model is saved to your account and tied to your identity across Gemini features.
One notable detail is how the setup works. The creation flow looks web-based, which suggests you might not be limited to your phone. A desktop option would make the process easier and reinforce that this is meant to work across devices.
More than Apple’s Memoji
Memoji focuses on expression and simplicity, using a cartoon style that fits messaging and video calls. Google’s approach aims for a more realistic result that blends into generated visuals.
Instead of sending an animated face, you could place a lifelike version of yourself into AI-generated scenes. The build hints at prompts that let you insert yourself directly into content, pointing to deeper integration with Gemini’s creative tools.
This changes how you create. Rather than capturing new images each time, you work with a reusable asset that can be dropped into different scenarios.
There is a tradeoff. A more realistic scan raises questions about accuracy and privacy, and Google has not shared details on how those concerns will be handled.
What to expect next
The feature is still in development and has not been released in a working form. It comes from an app teardown, so the final version could change or may not launch at all.
Even so, the direction is becoming clearer. The shift from earlier names like Character to Avatar points to a broader identity system tied to Gemini. Combined with cross-device support, this looks like more than an XR experiment.
If it launches, it will likely appear first in Gemini’s creative tools, where quickly inserting yourself into visuals would have the most value. There is no timeline or confirmed availability yet, so for now this remains an early look at where Google’s AI tools are heading.
