Upload a stereo audio file to transcribe and analyze.
Total Duration: s
| Metric | Channel 1 | Channel 2 | What it means |
|---|---|---|---|
| Speech Duration | Total active speaking time, ignoring silences. | ||
| Word Count | Total number of transcribed words. | ||
| Pace (WPM) | Speaking speed. Normal conversation is 120-160 WPM. | ||
| Pause Analysis | |||
| Total Pauses | Number of times the speaker paused between phrases. | ||
| Average Pause | The typical length of a pause. | ||
| Median Pause | The middle value of all pauses, ignoring extreme outliers. | ||
| Max Pause | The single longest gap in speech. | ||
| Moderate Pauses (>1.5s) | Typical pauses for taking a breath or organizing thoughts. | ||
| Long Pauses (>3.0s) | Indicates hesitation, searching for info, or system delays. | ||
| Vocal Pitch (Hz) | |||
| Mean Pitch | The average vocal frequency. | ||
| Pitch Range (Min - Max) | The absolute lowest and highest vocal frequencies detected. | ||
| Expressiveness (Std Dev) | High value = dynamic inflection. Low value = monotone delivery. | ||
Measures moments where both channels speak simultaneously.
Compares the speaking energy of both participants.
Speed Difference: A high gap means one person is rushing while the other is slow.
Pace Ratio: A ratio of exactly 1.0 means both speakers are talking at the exact same speed, showing high conversational alignment. Example : A ratio of 0.7 means Ch 1 is speaking at 70% the speed of Ch 2.