Hume Expression Measurement Api

Operator submits a batch job over a set of audio files and wants both vocal-prosody and spoken-language expression signals.

In the POST /v0/batch/jobs models config, enable the modalities that match the media and goal (prosody for vocal expression, language for transcript-derived expression); only enable face for video/image inputs. Each model returns its own per-frame/per-utterance expression scores.

Audio contains laughs, sighs, and gasps the operator wants characterized separately from spoken prosody.

Enable the vocal-burst model for non-linguistic vocalizations; keep its outputs distinct from the prosody model's speech-based scores. Do not merge burst and prosody outputs into one undifferentiated score set.

The job enables the face model but the submitted files are audio-only WAVs; the predictions for face come back empty.

Validate that each enabled model matches the media type before submit; on empty face predictions for audio input, recognize the mismatch rather than reporting 'no expression detected'. Surface a configuration error, not a false negative.