video-edit

Automate end-to-end video editing for talking-head YouTube content.

Updated Aug 23, 2026

Search Tags:#ai #transcription #metadata #video-editing #youtube-upload #silence-removal

Ready to run

npx skills add https://github.com/dudleypeacockqa/leverage_flo_website_marketing_agency --skill video-edit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: video-edit
Source: https://github.com/dudleypeacockqa/leverage_flo_website_marketing_agency/tree/main/.bible/aios/skills/video-edit
Command: npx skills add https://github.com/dudleypeacockqa/leverage_flo_website_marketing_agency --skill video-edit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, torchaudio, silero-vad, openai-whisper, faster-whisper, anthropic, python-dotenv, requests, and includes scripts (resource) components.

What problem does it solve?

End-to-end AI-driven video editing for talking-head YouTube content, delivering polished audio and clear metadata.

Core Features & Use Cases

Silence removal via neural VAD (Silero) or FFmpeg-based methods to eliminate dead air.
Audio mastering, transcription (Whisper), auto-generated chapters/descriptions, and YouTube/Auphonic upload support.
Optional swivel teaser introductions and LUT-based color grading to enhance branding and engagement.

Quick Start

Provide a raw talking-head video path to start an end-to-end edit and auto-generated metadata.

Frequently Asked Questions about video-edit

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

FAQPage Schema

How do I remove silence from talking-head videos for YouTube automatically?▼

You can remove silence from talking-head videos automatically using neural VAD via Silero or FFmpeg-based methods. This eliminates dead air from raw Screen Studio or DaVinci recordings before applying audio mastering and transcription.

Can I auto-generate YouTube chapters and descriptions from video transcriptions?▼

Yes, you can auto-generate YouTube chapters and descriptions from transcriptions. The workflow uses Whisper or faster-whisper to transcribe audio, then automatically creates structured metadata for your YouTube upload.

Do I need an Auphonic account for AI-powered video editing workflows?▼

Yes, you need an Auphonic account for audio mastering and upload support within this workflow. You also need Silero VAD and Whisper to handle silence removal and transcription.

What is the best way to add LUT-based color grading and swivel teasers to raw recordings?▼

The best way to add LUT-based color grading and swivel teasers to raw recordings is through an automated editing workflow. This enhances branding and engagement before uploading to YouTube.

Does faster-whisper work with FFmpeg for transcription and silence removal?▼

Faster-whisper handles transcription while FFmpeg manages silence removal. They function together within an end-to-end pipeline to process audio and generate metadata for talking-head content.

When should I not use neural VAD for silence removal in video editing?▼

You should avoid neural VAD for silence removal when working outside talking-head content or when FFmpeg-based methods are sufficient. Neural VAD via Silero is optimized for raw Screen Studio or DaVinci recordings.