Skip to main content

Getting started

The Imentiv API detects emotion in video, audio, images and text. It comes in two shapes, and which one you want depends on whether the media already exists.

Analyse a fileAnalyse a live feed
You sendA file or a URL, over HTTPSCamera and microphone, over WebRTC
You get backA full analysis when processing finishesResults streaming back within about a second
ShapeOrdinary REST callsREST to set up, WebSocket to read
Start hereVideo analysis quickstartRealtime session quickstart

Both describe emotion with the same vocabulary — the labels and measures in Understanding emotion scores — though the two surfaces do not carry an identical set of fields. That page says which belong to which.

What you need

  1. An API key. It's on your dashboard at imentiv.ai/my-profile.
  2. Credits. Analysis is metered. Running out mid-session is a specific, handled condition rather than a generic failure — see Errors and retries.
  3. Nothing else. There is no SDK to install and no client library to pick. The REST and WebSocket surfaces documented here are the integration path.

Your first call

The cheapest way to confirm your key works:

curl -X POST https://devapi.imentiv.ai/v2/texts \
-F "text=I am genuinely delighted with how this turned out." \
-F "title=Key check" \
-H "X-API-Key: your_api_key"

Note the -F: the upload endpoints take form fields, not a JSON body. Sending Content-Type: application/json gets you a 422, whatever the key is.

A 401 means the key is wrong or missing — see Authentication.

Where to go next

  • Authentication — how the key travels, and the one place it travels differently.
  • Errors and retries — which failures are worth retrying, and which are not. Worth reading before you write the retry loop rather than after.
  • Limits and media — session ceilings, credential lifetimes, and the resolutions and codecs the pipeline is tuned for.
  • API reference — every endpoint, with its request and response shapes.