---
name: audio-silence-trimmer
description: Find and remove long silences, ums, and ahs in raw audio with configurable thresholds — for podcast and voiceover cleanup.
title: Audio Silence Trimmer
category: voice-audio
difficulty: beginner
author: admin
icon: 🔇
input: audio
output: audio
phase: enhance
domain: content
tags: audio-cleanup,silence-detection,podcast-editing,rms-level,voiceover,filler-word-removal,edit-decision-list,ffmpeg,speech-model,audio-processing
best_for:
  - Podcast production and editing
  - Voiceover cleanup and post-production
  - Interview audio normalization
  - Audiobook editing
---

## 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.

## 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

1. 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.