skills.rest
larus-peritus
larus-peritusCOMMUNITY
Explore all skills by this author →
GitHub

Video Processor

Extract audio, convert formats, and transcribe videos via a unified CLI.

Updated Jan 19, 2026
Search Tags:#automation#CLI#transcription#whisper#ffmpeg#video-processing#audio-extraction
One-click install
npx skills add https://github.com/larus-peritus/pel_web --skill video-processor-larus-peritus
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Video Processor
Source: https://github.com/larus-peritus/pel_web/tree/main/.claude/skills/video-processor
Command: npx skills add https://github.com/larus-peritus/pel_web --skill video-processor-larus-peritus

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies complex video workflows by unifying audio extraction, format conversion, and transcription under a single CLI, saving time for creators and engineers.

Core Features & Use Cases

  • Audio extraction from video files using FFmpeg to prepare content for transcription or archiving.
  • Format conversion to MP4 or WebM with configurable codecs, presets, and audio encoding options.
  • Transcription of extracted audio with OpenAI's Whisper, supporting multiple languages and output formats (txt, srt, vtt, json).

Quick Start

  • Example: Extract audio from input.mp4 to output.wav: uv run .claude/skills/video-processor/scripts/video_processor.py extract_audio input.mp4 output.wav --format wav
  • Example: Convert input.avi to MP4: uv run .claude/skills/video-processor/scripts/video_processor.py to_mp4 input.avi output.mp4
  • Example: Transcribe video to transcript.txt with base model: 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 extract audio from a video file for transcription?▼

You can extract audio from video files using FFmpeg by running the CLI extract_audio command, specifying the input video and output audio file to generate WAV files ready for transcription.

How do I transcribe video to text using Whisper?▼

To transcribe video to text using Whisper, run the transcribe command with your input video and output file, selecting a Whisper model and output format like txt, srt, vtt, or json.

Can I convert video formats to MP4 and WebM using a CLI?▼

Yes, you can convert video formats to MP4 and WebM using the CLI's to_mp4 and format conversion commands, which support configurable codecs, presets, and audio encoding options.

What dependencies are needed for automated video processing?▼

Automated video processing requires click and ffmpeg-python dependencies, along with FFmpeg installed for media conversion and OpenAI's Whisper for audio transcription.

Does the video processing CLI support multiple languages for transcription?▼

Yes, the transcription feature supports multiple languages and output formats including txt, srt, vtt, and json, utilizing OpenAI's Whisper for accurate multilingual audio transcription.

What is the best way to automate end-to-end video processing workflows?▼

The best way to automate end-to-end video workflows is using a unified CLI that handles audio extraction, format conversion, and transcription, featuring robust error handling and dependency checks.

Related Skills

Explore More Software Engineering Skills→
marcusagmmarcusagm
4

ffmpeg

Generate ready-to-run FFmpeg commands for media conversion and processing.

Community
Advanced
winsorllcwinsorllc

youtube-transcript

Extract YouTube video transcripts in SRT, VTT, JSON, CSV, TSV, and plain text.

Community
Advanced
tkmh04tkmh04

media-processing

Automates image, audio, video batch resizing, conversion and optimization workflows using FFmpeg, ImageMagick, and Python scripts.

Community
Intermediate
MinhHoangDonoMinhHoangDono

ai-multimodal

Analyzes images, audio, and video and generates images and short videos via Gemini API.

Community
Intermediate