video-processor

Download, convert, and transcribe online videos using yt-dlp, FFmpeg, and Whisper.

1|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/xxih/ai-harness-zh --skill video-processor-xxih
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-processor
Source: https://github.com/xxih/ai-harness-zh/tree/main/references/translations/happy-claude-skills/skills/video-processor
Command: npx skills add https://github.com/xxih/ai-harness-zh --skill video-processor-xxih

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Downloading, converting, and transcribing videos from platforms like YouTube requires multiple tools and manual steps, making the process time‑consuming and error‑prone.

Core Features & Use Cases

  • Download videos from YouTube and many other supported sites, with options for audio‑only or subtitle embedding.
  • Convert formats between MP4, WebM, and extract audio in various codecs.
  • Transcribe audio using OpenAI Whisper with support for multiple languages and output formats such as txt, srt, vtt, and json.

Typical use cases include creating subtitles for educational content, extracting podcast audio for analysis, and preparing web‑ready video assets.

Quick Start

Ask the video‑processor skill to fetch and transcribe a YouTube video by providing its URL.

Frequently Asked Questions about video-processor

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

FAQPage Schema
How do I download and transcribe a YouTube video to text?

To download and transcribe a YouTube video, you provide the video URL. The tool fetches the media using yt-dlp and transcribes the audio to text using OpenAI Whisper, outputting subtitle files like srt or txt.

Can I extract audio only from a YouTube video for a podcast?

Yes, you can extract audio only from a YouTube video. The download process supports audio-only extraction, allowing you to pull podcast audio from supported platforms for analysis or offline listening.

Do I need FFmpeg and Whisper installed to convert video formats?

Yes, FFmpeg and Whisper must be installed in your environment. FFmpeg handles the video format conversion between MP4 and WebM, while Whisper is required specifically for the audio transcription feature.

What is the best way to generate SRT subtitles from an online video?

The best way to generate SRT subtitles is to use the transcription feature. It processes the downloaded audio with Whisper, supporting multiple languages and outputting subtitle formats including SRT, VTT, and JSON.

Does yt-dlp work with Vimeo and other platforms for media preparation?

Yes, yt-dlp works with Vimeo and many other supported sites. You can download videos from these platforms directly, preparing web-ready video assets or extracting media for further format conversion.

Why does video transcription stop working if FFmpeg is missing?

Video transcription stops working if FFmpeg is missing because the tool depends on it to process and decode audio. Both FFmpeg and Whisper are required dependencies in the environment to execute the transcription pipeline successfully.