Does this skill support subtitle generation?

Absolutely. It can output transcriptions in SRT and VTT formats, which are standard for video subtitles and web-based video players.

Can it process videos in languages other than English?

Yes, it supports Whisper's multi-language capabilities. You can either let the model auto-detect the language or specify a language code like 'es' for Spanish or 'fr' for French.

Can I choose the accuracy level of the transcription?

Yes, you can specify Whisper models ranging from 'tiny' (fastest) to 'large' (most accurate) depending on your hardware resources and quality requirements.

How does it handle video conversion for the web?

The skill includes a specific command to convert videos to WebM using the VP9 codec, which is optimized for high-quality web streaming and small file sizes.

What software dependencies are required for this skill?

You must have FFmpeg and OpenAI Whisper installed on your system. FFmpeg handles the media processing, while Whisper provides the speech-to-text capabilities.

Video Processor & Transcriber

Name: Video Processor & Transcriber
Author: Activer007

byActiver007

0•

Ciencia de Datos y ML

Automates video format conversion, audio extraction, and high-accuracy speech-to-text transcription using FFmpeg and Whisper.

This skill empowers Claude to handle complex multimedia tasks by providing a unified interface for FFmpeg and OpenAI's Whisper model. It allows for seamless conversion between video formats like MP4 and WebM, high-quality audio extraction, and the generation of precise transcriptions or subtitles in formats like SRT and VTT. Whether you are preparing content for the web, archiving legacy media, or requiring multilingual transcriptions, this skill streamlines the entire media processing workflow through automated scripts and environment validation.

Características Principales

01Export subtitles in SRT, VTT, and JSON formats with accurate timestamps.

02Automated temporary file management and environment dependency checks for FFmpeg and Whisper.

03Extract audio tracks from video files into WAV, MP3, AAC, or FLAC formats.

04Convert video files to universal MP4 or web-optimized WebM formats with customizable codecs.

050 GitHub stars

06Generate AI-powered transcriptions using OpenAI Whisper with support for various model sizes.

Casos de Uso

01Extracting audio from video recordings for standalone audio processing or podcasting.

02Converting legacy video formats to modern, web-compatible WebM or MP4 files.

03Generating multilingual subtitles and text transcripts for educational or interview videos.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add activer007/ordinary-claude-skills video-processor

For use in Claude.ai and ChatGPT

Download Skill