AudioEditor

Clean and edit audio recordings using Whisper, Claude, and ffmpeg.

17.4k|2.3k|Updated Sep 8, 2025

Search Tags:#audio processing #audio editing #AI transcription #podcast production #audio cleaning

Ready to run

npx skills add https://github.com/danielmiessler/LifeOS --skill audioeditor-danielmiessler

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: AudioEditor
Source: https://github.com/danielmiessler/LifeOS/tree/main/LifeOS/install/skills/AudioEditor
Command: npx skills add https://github.com/danielmiessler/LifeOS --skill audioeditor-danielmiessler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper, claude, ffmpeg, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of cleaning and editing audio recordings, removing unwanted elements like filler words, stutters, and dead air, resulting in professional-quality audio.

Core Features & Use Cases

Automated Audio Cleaning: Removes filler words, stutters, false starts, and dead air from audio recordings.
Transcription and Analysis: Transcribes audio to text and analyzes segments for editing decisions.
Editing and Polishing: Applies cuts with crossfades and optional cloud-based noise reduction.
Use Case: Ideal for podcasters, speakers, and anyone needing clean, professional audio.

Quick Start

Use the AudioEditor skill to clean up the audio file 'podcast-episode.mp3'.

Frequently Asked Questions about AudioEditor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate audio cleaning to remove filler words and dead air from podcast recordings?▼

Automated audio cleaning removes filler words, stutters, false starts, and dead air from recordings by transcribing audio with Whisper, classifying segments with Claude, and applying cuts with ffmpeg to produce polished audio.

How does AI transcription and segment classification work for audio editing?▼

AI transcription and segment classification works by using Whisper to transcribe the audio into text, then leveraging Claude to analyze those text segments and identify unwanted speech patterns for removal.

Do I need Whisper and ffmpeg installed to process audio streams and apply cuts?▼

Yes, you need Whisper, Claude, and ffmpeg installed. These dependencies are required to transcribe the audio, classify segments for editing decisions, and apply the actual cuts with crossfades.

Can I use this automated audio editing workflow for podcast production?▼

Yes, automated audio editing is ideal for podcast production, speech processing, and audio post-production workflows, handling the cleaning and polishing required for professional-quality recordings.

What is the best way to apply cuts with crossfades when editing audio recordings?▼

The best way to apply cuts with crossfades is through an automated pipeline that uses ffmpeg to process the audio streams based on segment classification, ensuring smooth transitions between the remaining audio segments.

Are there limitations when using Claude and Whisper for speech processing and audio post-production?▼

Limitations include reliance on the accuracy of Whisper transcription and Claude's segment classification for editing decisions, meaning complex audio contexts or heavy background noise might affect the automated cut precision.