Video Processor

Download videos, extract audio, convert formats, and transcribe with Whisper via CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/bingo-taiwan/claude-code-skills --skill video-processor-bingo-taiwan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Video Processor
Source: https://github.com/bingo-taiwan/claude-code-skills/tree/main/video-processor
Command: npx skills add https://github.com/bingo-taiwan/claude-code-skills --skill video-processor-bingo-taiwan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires click>=8.1.0, ffmpeg-python>=0.2.0, yt-dlp>=2024.0.0, and includes scripts (resource) components.

What problem does it solve?

This Skill consolidates video processing tasks into a single CLI, reducing manual steps for downloading, converting, and transcribing videos.

Core Features & Use Cases

  • Download videos from YouTube and thousands of sites using yt-dlp.
  • Extract audio for transcripts or analysis with FFmpeg.
  • Convert to MP4 or WebM formats for wide compatibility.
  • Transcribe audio/video using OpenAI's Whisper with configurable models.

Quick Start

Install FFmpeg, Whisper, yt-dlp and Python dependencies, then run the CLI for common tasks:

  • Download a video: uv run .claude/skills/video-processor/scripts/video_processor.py download 'https://youtube.com/watch?v=...' output.mp4
  • Extract audio: uv run .claude/skills/video-processor/scripts/video_processor.py extract_audio input.mp4 output.wav --format wav
  • Transcribe: uv run .claude/skills/video-processor/scripts/video_processor.py transcribe input.mp4 transcript.txt --model base --format txt

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 using yt-dlp and Whisper?

To download and transcribe YouTube video content, this CLI combines yt-dlp for fetching videos and Whisper for generating transcripts, handling audio extraction and text output in one workflow.

What do I need to install before converting video formats to MP4 or WebM with FFmpeg?

Converting video formats to MP4 or WebM requires FFmpeg, Whisper, yt-dlp, and Python dependencies like ffmpeg-python to be installed, ensuring the CLI can process and transcode media files properly.

Can I extract audio from a video and save it as a WAV file for transcription?

Yes, extracting audio as a WAV file is supported through FFmpeg integration, allowing you to isolate the audio track from video files and prepare it for Whisper transcription or separate analysis.

Does this video processing tool support configurable Whisper models for transcription?

Yes, the transcription functionality exposes configurable Whisper models, letting you specify the model size and language parameters to control transcription accuracy and processing speed.

What is the best way to convert downloaded videos to WebM format for web compatibility?

The best way to convert downloaded videos to WebM is using a CLI that wraps FFmpeg, handling the format conversion directly after the download step to ensure wide compatibility for web playback.

Are there limitations when using yt-dlp to download videos from thousands of sites?

While yt-dlp supports downloading from thousands of sites, limitations include requiring a stable network connection and proper installation of FFmpeg, Whisper, and yt-dlp to handle platform-specific restrictions or media formats.