Vocal burst

The vocal burst model measures 48 dimensions of emotional expression from non-linguistic vocalizations such as laughs, sighs, gasps, cries, and other sounds that carry emotional meaning but are not words. Recommended input filetypes: .wav, .mp3, .mp4.

Job configuration

The vocal burst model has no configurable parameters in either API. Enable it by passing an empty object:

$
curl -X POST "https://api.hume.ai/v0/batch/jobs" \
>
  -H "X-Hume-Api-Key: <YOUR_API_KEY>" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "models": {
>
      "burst": {}
>
    },
>
    "urls": ["https://example.com/audio.mp3"]
>
  }'

Output

Each prediction includes:

• Time interval: the begin and end timestamps in seconds
• Emotion scores: scores for each of the 48 expressions
• Descriptions: scores for each of the 67 burst types (e.g., “Laugh”, “Sigh”, “Gasp”)

1
{
2
  "grouped_predictions": [
3
    {
4
      "id": "unknown",
5
      "predictions": [
6
        {
7
          "time": {
8
            "begin": 2.50,
9
            "end": 3.10
10
          },
11
          "emotions": [
12
            { "name": "Amusement", "score": 0.892 },
13
            { "name": "Joy", "score": 0.721 },
14
            ...
15
          ],
16
          "descriptions": [
17
            { "name": "Laugh", "score": 0.945 },
18
            { "name": "Sigh", "score": 0.012 },
19
            ...
20
          ]
21
        }
22
      ]
23
    }
24
  ]
25
}

Burst types

The model can detect a wide range of vocal burst types, from laughter and cheering to gasps and groans.

Expressions

The vocal burst model measures the following 48 expressions. These are the same expressions measured by the facial expression and speech prosody models.