Classify multilabel emotion

Emotion only. With oruk-resonance (the default) the request runs the Resonance encoder and affect head; the transcription decoder is never invoked and the response contains no transcript text. One minute of audio uses one plan minute, exactly as unified analysis does.

post/v1/audio/emotions

Request

  • Base URL: https://speech-api.oruk.ai
  • URL: https://speech-api.oruk.ai/v1/audio/emotions
  • Auth: HTTP bearer

Headers

X-Request-IDstring

Unique request identifier. Reuse returns 409 and never creates a second debit.

Response

Speech result and measured usage

idstring required
object'speech.result' required
task'transcription' | 'emotion' | 'style' | 'affect' | 'analysis' | 'proficiency' required
modelstring required
textstring nullable
tagged_textstring nullable

Model-specific annotated transcript, not XML or word-level affect alignment. Resonance analysis may append unpaired <|label|> tags after a segment to annotate that segment. Use the structured segment emotions/styles arrays and start/end times for timed labels.

languagestring nullable
durationnumber required
diarizedboolean

True when segments are speaker turns (diarize=true).

speakersstring[]

Speaker labels in order of first appearance; empty unless diarized.

Changes

No recorded changes to this operation across all 1 revision of this API.