Silence Detection

Silence Detection scans your audio for quiet segments and creates removable markers on the timeline. It is useful for trimming leading and trailing silence, removing long pauses in speech, and cleaning up dead air in conversations.

Detection parameters

• Silence threshold: Segments quieter than this level are treated as silence. The default works well for indoor speech; raise it slightly if there is more background noise.
• Minimum duration: Only silence longer than this value is flagged. Shorter breaths and natural pauses are preserved.
• Padding: A small buffer is kept around each cut so sentences do not sound abruptly chopped.

How to use

1. Import your media and let waveform analysis finish.
2. Open Silence Detection and choose a preset that matches your content type (podcast, course, interview).
3. Review the markers on the timeline and listen to each segment.
4. Apply the deletions or export the cut list.

How it differs from Smart Pre-editing

Feature	Target	Result
Silence Detection	Silent or near-silent audio	Delete markers
Smart Pre-editing	Filler words, repeats, long pauses	Suggested markers

You can use both together: run Silence Detection first to clear obvious gaps, then use Smart Pre-editing to refine the speaking rhythm.

Notes

• Music, laughter, and low-volume conversation may be detected as silence. Always preview before applying.
• In multi-speaker conversations, short silences are sometimes part of the delivery. Avoid deleting all of them.
• The current version runs on a local model and does not upload audio to the cloud.