01
Upload completed audio
Send a supported file after the call. API v1 is prerecorded and does not claim real-time intervention.
Contact-center intelligence
Find the calls that need a careful human review
Analyze completed customer-service audio for a transcript, multilabel emotion, speaking style, and time-local segments. Use the output to prioritize review and understand patterns without pretending a score is a person’s inner state.
One file / one result
Searchable call content with acoustic context attached
I have already explained this twice, and I need someone to resolve it today.
frustrated 0.91impatient 0.78energetic 0.42
Unified analysis request
curl https://speech-api.oruk.ai/v1/audio/analysis \
-H "Authorization: Bearer $ORUK_API_KEY" \
-H "X-Request-ID: $(uuidgen)" \
-F "model=oruk-resonance" \
-F "file=@recording.wav"Workflow
02
Receive aligned outputs
Store the transcript, labels, segments, request ID, and usage record in the existing QA workflow.
03
Route human review
Combine the acoustic signal with operational context, policy checks, and qualified reviewer judgment.
Useful applications
- Prioritize a manageable review queue
- Compare aggregate patterns across queues or time periods
- Locate moments for coaching and quality review
- Add acoustic context to transcript search
Deployment safeguards
- Do not use emotion labels as the sole employee-performance measure
- Validate on the microphones, languages, accents, and call types in production
- Retain uncertainty and multiple labels rather than one definitive state
- Disclose recording and analysis according to applicable consent rules