Video Processor

Convert videos to MP4 and WebM, extract audio, and transcribe with Whisper.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/qdhenry/Foundry-OSS --skill video-processor-qdhenry
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Video Processor
Source: https://github.com/qdhenry/Foundry-OSS/tree/main/.agents/skills/video-processor
Command: npx skills add https://github.com/qdhenry/Foundry-OSS --skill video-processor-qdhenry

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires click>=8.1.0, ffmpeg-python>=0.2.0, and includes scripts (resource) components.

What problem does it solve?

Video files often require multiple separate tools to obtain a shareable format, extract audio for podcasts, and generate transcripts. This skill bundles conversion, audio extraction, and transcription into a single workflow.

Core Features & Use Cases

  • Audio extraction from video files (e.g., mp4, mov) for podcasts or analysis.
  • Format conversion to MP4 and WebM for web compatibility.
  • Transcription of audio using Whisper for searchable transcripts and captions. Use Case: A content team receives video lectures and needs MP4 versions for a site, audio-only files for podcasts, and transcripts for accessibility.

Quick Start

Convert a video file to MP4, extract its audio, and transcribe the audio with Whisper.

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 an MP4 video and transcribe it to text?

You can extract audio from an MP4 video and transcribe it to text by using a single CLI workflow that leverages FFmpeg for audio extraction and Whisper for transcription, automating both tasks with built-in file validation and error handling.

Can I convert video files to WebM and MP4 formats for web compatibility?

Yes, you can convert video files to WebM and MP4 formats for web compatibility. The workflow automates format conversion using FFmpeg, ensuring your video assets are web-ready while validating input files and handling errors during the process.

Do I need FFmpeg and Whisper installed to automate video processing tasks?

Yes, you need FFmpeg and Whisper installed to automate video processing tasks. FFmpeg handles audio extraction and format conversion to MP4 or WebM, while Whisper performs the transcription, with both dependencies required for the CLI to orchestrate the workflow.

What is the best way to generate searchable transcripts from video lectures?

The best way to generate searchable transcripts from video lectures is to use an automated workflow that extracts the audio track with FFmpeg and then passes it to Whisper for transcription, bundling both steps into a single command-line process with error handling.

Does this video processing workflow validate input files before conversion and transcription?

Yes, this video processing workflow validates input files before conversion and transcription. It checks file inputs before orchestrating the audio extraction, MP4 or WebM conversion, and Whisper transcription tasks, providing error handling throughout the process.