Video Processor

Extracts audio, converts video to MP4 or WebM, and transcribes with Whisper via Python CLI.

1.5k|387|Updated Jul 13, 2025
One-click install
npx skills add https://github.com/disler/claude-code-hooks-multi-agent-observability --skill video-processor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Video Processor
Source: https://github.com/disler/claude-code-hooks-multi-agent-observability/tree/main/.claude/skills/video-processor
Command: npx skills add https://github.com/disler/claude-code-hooks-multi-agent-observability --skill video-processor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires click, ffmpeg-python, and includes scripts (resource) components.

What problem does it solves? Manually processing video files for different formats, extracting audio, or generating transcripts is time-consuming and requires specialized software. This Skill automates these common video tasks, making it easy to prepare videos for web, extract audio for podcasts, or generate accurate subtitles, saving you valuable time.

Core Features & Use Cases

  • Audio Extraction: Pull audio tracks from any video file into formats like WAV or MP3, perfect for podcast creation or audio analysis.
  • Video Conversion: Convert videos to web-friendly formats like MP4 and WebM, ensuring optimal playback across platforms.
  • Whisper Transcription: Generate highly accurate text transcripts from video or audio, with support for multiple languages and output formats (SRT, VTT, TXT, JSON) for accessibility and content repurposing.
  • Use Case: You have a recorded webinar and need to upload it to your website, create a podcast version, and generate subtitles for accessibility. Use this skill to convert the video to WebM, extract the audio as MP3, and transcribe it to an SRT file, all in a few commands.

Quick Start

Transcribe the attached video file 'meeting_summary.mp4' into a text file named 'summary.txt'.

Frequently Asked Questions about Video Processor

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

FAQPage Schema
How do I extract audio from a video file?

Audio extraction pulls audio tracks from video files into formats like WAV or MP3. This Skill uses FFmpeg to extract audio from any video format, useful for podcast creation, audio analysis, or repurposing video content into standalone audio files.

Can I convert videos to MP4 and WebM formats?

Yes, video conversion transforms files into web-friendly MP4 and WebM formats for cross-platform playback. This Skill automates the conversion process, ensuring optimal quality and compatibility across browsers and devices without manual encoding.

How do I generate transcripts and subtitles from video?

Transcription uses OpenAI Whisper to generate accurate text from video or audio with support for multiple languages and output formats: SRT, VTT, TXT, and JSON. This enables accessibility, content repurposing, and searchable transcripts from multimedia files.

What video formats does this support for processing?

This Skill processes video files of various formats for audio extraction, conversion, and transcription. FFmpeg handles input validation and supports standard video formats, converting them to MP4, WebM, or extracting audio without format restrictions.

Can I automate multiple video tasks in one workflow?

Yes, end-to-end automation chains audio extraction, format conversion, and transcription together. The Python CLI provides commands—extract_audio, to_mp4, to_webm, and transcribe—enabling you to process videos completely without switching tools.

What output formats are available for transcripts?

Transcripts export as SRT, VTT, TXT, or JSON formats. Each format serves different purposes: SRT and VTT for subtitle embedding, TXT for plain text, and JSON for structured data integration or further processing and analysis.