Interhuman AI

Interhuman AI detects social signals from videos using its key product, Inter-1. This omni-modal model processes the video stream to identify the 'how' of communication, namely voice, face, and body language. The advanced detection of these social signals allows a comprehensive perception and interpretation of human behavior.

Yes, Inter-1 from Interhuman AI has the capability to process inputs from video, audio, and text simultaneously. The model is designed in such a way that it can holistically interpret these different modalities together to detect and understand social signals much more robustly and accurately.

Being omni-modal means that Interhuman AI can perceive and interpret signals from multiple sensory modalities simultaneously, specifically video, audio, and text. This behaviour allows for a comprehensive detection and understanding of social signals across these different input types.

Interhuman AI provides structured feedback on communication methods. It delivers evidence-backed evaluations of social signals, rather than subjective inputs. This feedback can be utilized to improve communication skills by understanding voice, face, and body language aspects and their impact on a conversation.

Interhuman AI incorporates behavioral science into its technology by deploying its root technology, Inter-1, designed based on the principles of behavioral science. Additionally, it detects a range of 12 social signals that are grounded in behavioral science, providing meaningful interpretations across different conversations.