> This page is for Expression Measurement.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://dev.hume.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://dev.hume.ai/_mcp/server.

# Video measurements

**The image upload and video realtime endpoints return two arrays of scores for each measured face: `expressions` and `descriptions`.** Both are `null` for a face beyond the [limit on measured faces](/expression-measurement/docs/video/upload#detection). [Scores](/expression-measurement/docs/scores) explains how to read them. The video and audio endpoints use different expression names.

#### Face (excerpt)

```json
{
  "expressions": [
    {
      "name": "amusement",
      "probability": 0.7124
    },
    {
      "name": "joy",
      "probability": 0.5308
    }
  ],
  "descriptions": [
    {
      "name": "smile",
      "probability": 0.8419
    },
    {
      "name": "grin",
      "probability": 0.3172
    }
  ]
}
```

## Expressions

Emotions and mental states a person viewing the face would name, such as `amusement` and `concentration`. 48 names.

<table searchable>
  <tbody>
    <tr>
      <td>
        `admiration`
      </td>

      <td>
        `contemplation`
      </td>

      <td>
        `entrancement`
      </td>

      <td>
        `realization`
      </td>
    </tr>

    <tr>
      <td>
        `adoration`
      </td>

      <td>
        `contempt`
      </td>

      <td>
        `envy`
      </td>

      <td>
        `relief`
      </td>
    </tr>

    <tr>
      <td>
        `aesthetic appreciation`
      </td>

      <td>
        `contentment`
      </td>

      <td>
        `excitement`
      </td>

      <td>
        `romance`
      </td>
    </tr>

    <tr>
      <td>
        `amusement`
      </td>

      <td>
        `craving`
      </td>

      <td>
        `fear`
      </td>

      <td>
        `sadness`
      </td>
    </tr>

    <tr>
      <td>
        `anger`
      </td>

      <td>
        `determination`
      </td>

      <td>
        `guilt`
      </td>

      <td>
        `satisfaction`
      </td>
    </tr>

    <tr>
      <td>
        `anxiety`
      </td>

      <td>
        `disappointment`
      </td>

      <td>
        `horror`
      </td>

      <td>
        `sexual desire`
      </td>
    </tr>

    <tr>
      <td>
        `awe`
      </td>

      <td>
        `disgust`
      </td>

      <td>
        `interest`
      </td>

      <td>
        `shame`
      </td>
    </tr>

    <tr>
      <td>
        `awkwardness`
      </td>

      <td>
        `distress`
      </td>

      <td>
        `joy`
      </td>

      <td>
        `surprise (negative)`
      </td>
    </tr>

    <tr>
      <td>
        `boredom`
      </td>

      <td>
        `doubt`
      </td>

      <td>
        `love`
      </td>

      <td>
        `surprise (positive)`
      </td>
    </tr>

    <tr>
      <td>
        `calmness`
      </td>

      <td>
        `ecstasy`
      </td>

      <td>
        `nostalgia`
      </td>

      <td>
        `sympathy`
      </td>
    </tr>

    <tr>
      <td>
        `concentration`
      </td>

      <td>
        `embarrassment`
      </td>

      <td>
        `pain`
      </td>

      <td>
        `tiredness`
      </td>
    </tr>

    <tr>
      <td>
        `confusion`
      </td>

      <td>
        `empathic pain`
      </td>

      <td>
        `pride`
      </td>

      <td>
        `triumph`
      </td>
    </tr>
  </tbody>
</table>

## Descriptions

Facial actions visible on the face, such as `smile` or `jaw drop`. 27 names. Each `probability` is the chance that the action is present. See [Scores](/expression-measurement/docs/scores#reading-probabilities).

<table searchable>
  <tbody>
    <tr>
      <td>
        `beaming`
      </td>

      <td>
        `frown`
      </td>

      <td>
        `laugh`
      </td>

      <td>
        `squint`
      </td>
    </tr>

    <tr>
      <td>
        `biting lip`
      </td>

      <td>
        `gasp`
      </td>

      <td>
        `licking lip`
      </td>

      <td>
        `sulking`
      </td>
    </tr>

    <tr>
      <td>
        `cheering`
      </td>

      <td>
        `glare`
      </td>

      <td>
        `pout`
      </td>

      <td>
        `tongue out`
      </td>
    </tr>

    <tr>
      <td>
        `cringe`
      </td>

      <td>
        `glaring`
      </td>

      <td>
        `scowl`
      </td>

      <td>
        `wide-eyed`
      </td>
    </tr>

    <tr>
      <td>
        `cry`
      </td>

      <td>
        `grimace`
      </td>

      <td>
        `smile`
      </td>

      <td>
        `wince`
      </td>
    </tr>

    <tr>
      <td>
        `eyes closed`
      </td>

      <td>
        `grin`
      </td>

      <td>
        `smirk`
      </td>

      <td>
        `wrinkled nose`
      </td>
    </tr>

    <tr>
      <td>
        `face in hands`
      </td>

      <td>
        `jaw drop`
      </td>

      <td>
        `snarl`
      </td>

      <td />
    </tr>
  </tbody>
</table>

## Next steps

#### [Image upload](/expression-measurement/docs/video/upload)

Upload JPEG images and receive scores for the faces in each image.

#### [Video realtime](/expression-measurement/docs/video/realtime)

Detection settings, face tracking, and how results pair with frames.