ActionHume AIUpdated May 2026

How do I score audio/video for emotion with Hume?

Short answer: Drop the "Hume AI → Hume Expression Measurement" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 3 Hume AI actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
URLs urls	array	Required	Audio/video/text URLs to analyze
Face Model models_face	options	Optional	Face Model. Options: No, Yes
Voice/Prosody Model models_prosody	options	Optional	Voice/Prosody Model. Options: Yes, No
Language Model models_language	options	Optional	Language Model. Options: No, Yes

Sample request

{
  "urls": "{{trigger.urls}}",
  "models_face": "{{trigger.models_face}}",
  "models_prosody": "{{trigger.models_prosody}}",
  "models_language": "{{trigger.models_language}}"
}

Returns

{
  "job_id": "job_abc"
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Hume Expression Measurement.

Any of these apps can fire this action as part of a workflow.

Google Sheets → Hume AI

2 Google Sheets triggers

HubSpot → Hume AI

18 HubSpot triggers

FAQ

Questions about Hume Expression Measurement.

What does the Hume Expression Measurement action do in Hume AI?

Returns per-segment scores across 50+ emotion dimensions for audio, video, or text. For "is this customer call escalating in frustration?" or "score this user video reaction" workflows.

What inputs does Hume Expression Measurement require?

Required: URLs. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Hume AI returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Hume Expression Measurement support batch operations?

Yes. Run Hume Expression Measurement inside a Loop node to process arrays. Tiny Command handles Hume AI's rate limits automatically so you don't have to throttle manually.

More actions