Nuance Labs offers Human Foundation Model
Product
Full-duplex audiovisual foundation model for real-time face-to-face AI conversation.
- Currently Offered
Full-duplex audiovisual foundation model for real-time face-to-face AI conversation.
Human Foundation Model is Nuance Labs' full-duplex audiovisual system that perceives speech, facial expression, gaze, and timing while generating voice and visual responses in the same moment. It is designed so conversation with AI feels continuous rather than turn-based.
The model targets sub-500-millisecond conversational latency and supports active-listening behaviors such as backchanneling. Nuance Labs is preparing a public research preview for later in 2026.
Runway Characters creates real-time conversational video agents from a single image.
Runway Characters creates real-time conversational video agents from a single image.
Foundation Models are Mirage's multimodal audio and video models that generate realistic talking videos from text, audio, or images.
A web app that turns live video and screen context into a real-time AI body double for video calls.
Gemini Live API enables real-time voice and vision interactions through streaming conversational models.
Foundation models and AI agents for spatial-temporal reasoning in virtual and physical environments.
Foundation Models are Mirage's multimodal audio and video models that generate realistic talking videos from text, audio, or images.
A web app that turns live video and screen context into a real-time AI body double for video calls.
Gemini Live API enables real-time voice and vision interactions through streaming conversational models.
Foundation models and AI agents for spatial-temporal reasoning in virtual and physical environments.
26M-parameter open-source function-call model for small consumer devices.