Skip to main content

API Documentation

Imentiv API

Emotion AI for video, audio, images and text

Get started API reference

Analyse a file

Send media, poll for the result, read the emotion timeline. Same shape for all four.

VideoUpload a video and get per-face emotion over time, with speakers, transcripts and highlights.AudioVoice-tone emotion and diarised transcription for a recording, segment by segment.ImageFacial emotion, demographics and per-face notes for a still image.TextEmotion and sentiment for written text, with reporting.

RealtimeStream a live camera and microphone feed over WebRTC and receive facial emotion, voice tone, transcription and text emotion back over a WebSocket, within about a second. Ask questions about the session while it is still running.

Start here

GuidesAuthentication, quotas, errors and the end-to-end walkthroughs.ReferenceEvery endpoint, its parameters, and a live request you can send from the page.