Behavior detections
Behaviors Velma was configured to listen for on this call, with reasoning and evidence
| Speaker | Behavior | Reasoning and evidence | Confidence |
|---|
Velma Triage
0:00
0:00
0:00
Summary
Speakers
| Speaker | Speech pattern | Speaking time |
|---|
Behaviors
Transcript
Speech Summary
Speakers
| Speaker | Emotion pattern | Speaking time | Language |
|---|
Topics & Sentiment
Behaviors
| Speaker | Behavior | Model reasoning | Confidence |
|---|
Transcript
Upload an audio file or start streaming to see the transcript.
| Timestamp | Verdict | Confidence |
|---|
| Timestamp | Music | Speech |
|---|
Every window is checked independently for AI vocals and AI instrumentals — a track can flag on both at once. A dash means that detector had nothing to score in the window; a low score means it checked and the content looks real. Heavily processed or high-production songs may still false-positive.
| Window | Verdict | Vocal AI | Instrumental AI |
|---|
| Window | Emotion |
|---|
| Window | Accent |
|---|
Upload an audio file to see the redacted transcript.