01
Capture with consent
Record the meeting using the product’s existing consent and retention controls.
Meeting intelligence
Preserve how a recorded discussion unfolded, not only the words
Process completed meeting audio to return a searchable transcript with time-local emotion and speaking-style annotations. The result can help reviewers revisit moments where wording alone loses important delivery context.
One file / one result
One timeline for words and changes in delivery
That sounds promising. I still want to understand what happens if the timeline slips.
hopeful 0.72skeptical 0.61formal 0.48
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
Analyze after completion
Submit the file to unified analysis and retain only the response fields needed by the application.
03
Support review
Let users search transcript text, inspect time-local labels, and correct downstream interpretations.
Useful applications
- Retrieve moments with both text and delivery context
- Support qualitative meeting review
- Summarize aggregate expression patterns with uncertainty
- Improve search across recorded discussions
Deployment safeguards
- Do not infer agreement, honesty, intent, or private mental state from a label
- Keep access to sensitive meeting analysis tightly scoped
- Provide deletion and correction workflows in the host product
- Evaluate the actual room acoustics and microphone configuration