Skip to content
orukSign up
Speech-to-textVoice agentsModelsPricingResearchAPI docsQuickstartSDKsMCP serverIntegrationsBenchmarksStatusLog in

Emotion in an airplane announcement

Listen to “The airplane is almost full” and inspect how one recording receives several emotion scores alongside a tired speaking style.

Listen to the recording

A boarding announcement describes a fact. Can a service also represent several qualities in how the speaker delivers it?

Take 1 · 2.94 seconds

Transcript: “The airplane is almost full.”

Stored Resonance 1 scores, take 1
OutputLabelScore
emotionsworried0.992
emotionssad0.946
emotionsdisappointed0.915
stylestired0.982

Download take 1 (WAV)

Reading the scores

CREMA-D labels the performance as sad. The model also returned worried and disappointed. Each score is independent, so reducing this clip to a single winning label discards part of the output.

These acted English recordings were selected from the training split for demonstration. The scores describe audible delivery. Use a separate held-out set to measure accuracy.

Recording credits and licenses: CREMA-D. The public sample catalog includes each source file, audio hash and saved output.

Run this example

Shell · authenticated file analysis
curl --fail --location https://oruk.ai/samples/emotional/1038_TAI_SAD_XX.wav -o take.wav
curl --fail-with-body https://speech-api.oruk.ai/v1/audio/analysis \
  -H "Authorization: Bearer $ORUK_API_KEY" \
  -F file=@take.wav -F model=oruk-resonance

The example uses a key with speech API access. The table shows the saved run. Open the matching SDK quickstart.

Try it on your own audio.

The demo needs no account. The trial needs a card.