aiqbench takeAI Products

This update introduces a multimodal interface layer to the Gemini 3.8 Live model, enabling real-time lip-syncing and identity-preserving avatars for enterprise users. The core technical advancement lies in maintaining video fidelity across 97 languages while integrating visual processing capabilities into the live inference pipeline. This represents a shift toward embodied AI interactions rather than a fundamental change in underlying model architecture or quantum computing principles.

Source coveringThe Verge

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Gemini 3.8 Live with Live Avatar gives Google’s AI a face

The VergeSeptember 24, 20262 min read

Google's new Gemini 3.8 Live update lets users have conversations with the model while watching an animated AI persona respond in real time. The "Live Avatar" will lip-sync and show different facial expressions during conversations, but it's currently only available to Gemini Enterprise customers. As noted by Google, Live Avatar can transition between the 97 languages it supports "without degrading video fidelity or introducing visual drift." One video shared by Google shows its Live Avatar talking in English and Japanese, with its mouth animation lining up with what it's saying in both languages. It can also pull up information on-screen w … Read the full story at The Verge.

is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer…

Excerpt shown under the publisher's RSS terms · 22 words · full text and figures are on the publisher's site

Read at The Verge ↗Ask about this article