Skip to main content

​
Detect and interpret conversational behavior.

Interhuman is the social intelligence API for developers to detect and interpret engagement state, social signals, and conversation quality in real-time or post-processing.

​
How to integrate

Inter-1 Analyze uploaded video

Upload video files for comprehensive behavioral analysis.

Inter-1 Stream Analysis

Stream raw video data for real-time interpretation.

Inter-2 and Inter-2 Audio Upload Analysis

Upload a video file for Inter-2, or an audio file for Inter-2 Audio, and read the analysis back as a job.

Inter-2 and Inter-2 Audio Stream Analysis

Stream video to Inter-2, or audio alone to Inter-2 Audio, for real-time interpretation.

​
Capabilities

The API provides access to models that analyze video (Inter-1 and Inter-2) or audio alone (Inter-2 Audio) and produce:
  • Engagement State: Time-bounded states such as engaged, disengaged, and neutral states.
  • Social Signals: Agreement, confusion, interest, and more with timing, probability, and rationale. Inter-2 Audio reports the six signals that can be heard.
  • Conversation Quality: Aggregate and timeline scores for energy, rapport, authority, learning, and clarity.

​
Authentication

Send your API key, or a client token minted from it, as Authorization: Bearer <credential>. Each endpoint requires a scope: interhumanai.upload for the upload endpoints and interhumanai.stream for the stream endpoints. See Authentication and Get an API key.