Audio Silence Trimmer
Find and remove long silences, ums, and ahs in raw audio with configurable thresholds — for podcast and voiceover cleanup.
🧠 Why it works
Manual silence-cutting in a DAW is the most tedious part of podcast editing. Level-based detection handles 95 percent of the cuts without quality loss; the remaining 5 percent (breaths you want to keep, dramatic pauses) are easy to un-cut from an edit list.
⚙️ How it works
- Compute a short-window RMS level across the audio. 2. Mark regions where the level stays below a dB threshold for more than the silence threshold. 3. Optionally detect filler words via a small speech model (Whisper tiny + regex for 'um|uh|ah|like') and add to the cut list. 4. Emit an edit decision list (EDL) with start/end timestamps. 5. Apply the EDL via ffmpeg with crossfades to prevent clicks. 6. Output the cleaned audio plus the EDL so edits can be reviewed or reverted.
Description
Input: raw audio file. Output: a cleaned audio file with silences longer than N seconds shortened to a configurable gap, and optionally the detected ums/ahs removed. Emits a timestamped edit list so the cuts are auditable and reversible.
Install this skill
A Claude skill is a skill.md file with YAML frontmatter and a markdown body.
Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.
mkdir -p ~/.claude/skills/audio-silence-trimmer \
&& curl -L https://aidiveforge.com/skill/audio-silence-trimmer.skill-md \
-o ~/.claude/skills/audio-silence-trimmer/skill.mdSave to ~/.claude/skills/audio-silence-trimmer/skill.md
Recommended Use
Sign in to suggestTools and workflow packs this skill pairs well with. Forge picks are auto-generated from category + capability signals; Community picks are added by people who've used the pairing.
Forge Auto-recommended matches
Tools
Workflow packs
Report compatibility
Tell the community which tool you used this skill with, and whether it worked.
Suggest a pairing
Recommend a tool or workflow pack that this skill works well with. Up to 5 recommendations per day.