Microsoft is giving Copilot AI faces you can chat with

""they'd feel more comfortable talking to a face when using voice.""

""This experiment leverages VASA-1, an advanced AI technology developed by Microsoft Research to create real-time, visual AI conversations,""

""The innovation allows us to generate natural facial expressions, head movements, and lip-sync from just a single image - no complex 3D modeling required.""

""Each portrait is intentionally stylized and not photorealistic, offering you visual variety while offering the same trusted Copilot intelligence and safety features you rely on,""

Portraits in Copilot Labs provides 40 stylized human avatars that display natural expressions during real-time voice conversations. The feature is available in the US, UK, and Canada and enables users to pair a chosen portrait with a voice to make verbal interactions feel more natural. VASA-1, developed by Microsoft Research, generates facial expressions, head movements, and lip-sync from a single image without complex 3D modeling. Portraits intentionally avoid photorealism and follow earlier efforts to give Copilot character, while the rollout is cautious due to safety concerns and competing avatar features from other AI providers.

Read at The Verge