Skip to main content
Build a small app that uploads a video from your computer to Interhuman and returns structured analysis results. In this codealong, you will:
  • exchange your key_id and key_secret for an access token
  • upload a local video to POST /v1/upload/analyze
  • optionally request conversation-quality outputs
  • render returned signals[] (including per-signal rationale) and quality metrics in your UI
This page is written so you can follow the build without the video, while the video helps with pacing and implementation details.

​
Watch the codealong video

Keep the video and your editor side by side; pause after each major step. Reference implementation: interhuman-video-analyzer-codealong on GitHub

​
Build steps

​
1) Prepare credentials and auth

Before calling upload, make sure you have an API key from platform.interhuman.ai. If needed, follow Get an API key. Then exchange your key_id and key_secret for an access token using the Authentication endpoint, and request the interhumanai.upload scope. Without this scope, upload requests will fail with an insufficient-scope error.

​
2) Add a simple file-upload UI

Create a minimal UI with:
  • a file input that accepts a local video file
  • an Analyze button
  • a results panel (for JSON output or parsed cards)
For this codealong, keep it simple. A plain HTML input and a single action button are enough to validate your integration end to end.

​
3) Call Upload & Analyze

When the user clicks Analyze, send the selected file to:
  • POST /v1/upload/analyze
  • with Authorization: Bearer <access_token>
  • as multipart form data (file)
Reference: Upload & Analyze API

​
4) Optionally include conversation quality

You can request conversation-quality outputs with include flags:
  • conversation_quality_overall
  • conversation_quality_timeline
If included, the API returns conversation quality both as a single overall view and as timeline windows. References:

​
5) Render results in the app

Once processing completes, render the response in your results panel. At minimum, show:
  • signals[] entries (type, start, end, probability, rationale)
  • optional conversation_quality.overall
  • optional conversation_quality.timeline[]
This gives users both event-level insight (what happened and why) and quality-level insight (how the interaction performed across time).

​
What to inspect in the response

  • Signal timing: start/end are in seconds from the beginning of the uploaded video.
  • Probability: confidence bucket for each detected signal.
  • Rationale: a structured explanation of observed behavior (for example speech pauses, tone shifts, gaze, and pacing cues).
  • Conversation quality: overall plus core dimensions (quality_index, energy, rapport, authority, learning, clarity), and optionally a timeline that shows change over time.

​
Next steps