video-processor
Video Processor handles end-to-end video workflows: download from YouTube and thousands of other sites, convert between formats, pull audio tracks, and generate transcripts via Whisper. Built on yt-dlp, FFmpeg, and OpenAI's speech model.
Video Processor downloads videos from YouTube and other platforms, then converts formats, extracts audio, and transcribes with Whisper.
AI-generated summary based on this skill's SKILL.md
Install
iamzhihuix/happy-claude-skills/video-processor · repository language: TypeScript
git clone https://github.com/iamzhihuix/happy-claude-skills
cp -r happy-claude-skills/skills/video-processor ~/.claude/skills/video-processornpx skillfed install iamzhihuix/happy-claude-skills/video-processorFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I download a YouTube video to MP4 with video-processor?
Video-processor downloads YouTube videos and thousands of other platforms using yt-dlp integration. Specify your URL and output format—video-processor handles the download and saves it as MP4 or your chosen format. The tool supports batch operations, so you can process multiple videos in one run.
Can video-processor extract audio from video files?
Yes. Video-processor extracts audio tracks from video files and converts them to formats like MP3, WAV, or AAC. It uses FFmpeg under the hood to handle various input formats (AVI, MOV, MKV, etc.) and produces clean audio output without re-encoding the entire video.
What does video-processor use to transcribe video to text?
Video-processor uses OpenAI's Whisper model to transcribe audio and video content to text. It automatically extracts the audio track, processes it through Whisper, and returns a full transcript. The tool supports multiple languages and can generate timestamped transcripts for easier navigation.
How do I convert video between MP4, WebM, and other formats?
Video-processor converts between MP4, WebM, AVI, MOV, and other formats using FFmpeg. Specify your input file and desired output format—video-processor handles codec selection, bitrate optimization, and quality settings automatically, or you can customize parameters for advanced use cases.
Can video-processor generate subtitles and transcripts with language support?
Video-processor generates subtitles and transcripts via Whisper with support for multiple languages. It can create SRT subtitle files with timestamps, plain-text transcripts, or JSON output. Language detection is automatic, but you can specify a language to improve accuracy for non-English content.
What license does video-processor use?
Video-processor is released under the MIT license, allowing free use, modification, and distribution in both open-source and commercial projects. See the LICENSE file in the repository for full terms.
SKILL.md
rendered from the published skill — quoted content, verbatim
Video Processor
Instructions
This skill provides comprehensive video processing utilities including YouTube video download, audio extraction, format conversion, and audio transcription using yt-dlp, FFmpeg, and OpenAI's Whisper model.
Prerequisites
Required tools (must be installed in your environment): - yt-dlp: Video downloader for YouTube and thousands of other sites ```bash # Install via pip pip install -U yt-dlp
# Verify installation yt-dlp --version ```
- FFmpeg: Multimedia framework for video/audio processing ```bash # macOS brew install ffmpeg
# Ubuntu/Debian apt-get install ffmpeg
# Verify installation ffmpeg -version ```
- OpenAI Whisper: Speech-to-text transcription model ```bash # Install via pip pip install
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 2 files
skills/video-processor/SKILL.md
skills/video-processor/scripts/video_processor.py