media-hub

Convert media formats and transcribe audio using FFmpeg and Whisper.

28|13|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/wulaosiji/skills --skill media-hub-wulaosiji
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media-hub
Source: https://github.com/wulaosiji/skills/tree/main/media_hub
Command: npx skills add https://github.com/wulaosiji/skills --skill media-hub-wulaosiji

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydub, moviepy, openai-whisper, Pillow, edge-tts, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines the complex and time-consuming tasks associated with processing various media files, including audio, video, and images.

Core Features & Use Cases

  • Format Conversion: Convert audio and video files between numerous formats (e.g., MP4 to MP3, WAV to MP3).
  • Transcription: Transcribe audio from video or audio files using the Whisper model.
  • Media Information: Extract detailed metadata about media files.
  • Use Case: Convert a recorded Zoom meeting video into an MP3 audio file, transcribe the audio into a text document, and then save the transcript for easy searching and analysis.

Quick Start

Use the media-hub skill to convert the video file 'meeting.mp4' to an audio file named 'meeting.mp3'.

Frequently Asked Questions about media-hub

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

FAQPage Schema
How do I extract audio from a video file and transcribe it to text?

To extract audio and transcribe video to text, this tool converts the video file to an audio format using FFmpeg, then applies the Whisper model to generate a searchable text transcript from the audio.

Can I convert MP4 to MP3 and other audio or video formats?

Yes, you can convert MP4 to MP3 and perform format conversion across numerous audio and video formats, handling various codecs robustly through its unified FFmpeg and pydub interface.

Does this media processing tool support image files alongside audio and video?

Yes, this media processing tool supports image files alongside audio and video, utilizing the Pillow library for comprehensive image manipulation within the same unified interface.

What is the best way to transcribe a recorded meeting using Whisper?

The best way to transcribe a recorded meeting using Whisper is to load the media file, extract the audio track, and execute speech-to-text transcription to output a text document for analysis.

Do I need FFmpeg installed to convert audio and video files?

Yes, FFmpeg is required as a core dependency to convert audio and video files, as the tool integrates directly with it and libraries like moviepy to ensure robust handling of various formats and codecs.

Can I use edge-tts to generate audio with this media processing skill?

Yes, edge-tts is included as a dependency, enabling text-to-speech audio generation alongside its core media conversion and speech-to-text transcription capabilities within the unified interface.