Can I control the accuracy of the transcription?

Yes, you can specify the Whisper model size (tiny, base, small, medium, or large) to balance processing speed with transcription accuracy.

What subtitle formats are supported?

The skill can output transcripts in plain text (txt), SubRip (srt), WebVTT (vtt), and detailed JSON format with word-level timestamps.

Does this skill require external software?

Yes, you must have FFmpeg and the OpenAI Whisper Python package installed in your local environment for this skill to function.

Can I transcribe videos in languages other than English?

Yes, you can specify a language code (e.g., 'es' for Spanish, 'fr' for French) or allow Whisper to auto-detect the language during the transcription process.

Which video formats can I convert to?

The skill provides optimized commands for converting video files to MP4 (using libx264/libx265) and WebM (using VP9).

Video Processor & Transcriber

Name: Video Processor & Transcriber
Author: Microck

byMicrock

•

Data Science & ML

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

About

This skill empowers Claude to handle complex multimedia tasks directly within the development environment by leveraging FFmpeg and OpenAI's Whisper model. It provides a streamlined CLI for converting videos to web-standard MP4 or WebM formats, extracting high-quality audio tracks, and generating accurate transcriptions in various formats like SRT, VTT, and JSON. Whether you are preparing assets for web deployment, generating subtitles for accessibility, or extracting data from recorded meetings, this skill automates the technical heavy lifting of media processing and AI-driven transcription.

Key Features

Support for multiple subtitle formats (SRT, VTT, TXT, JSON)
Automated speech-to-text transcription using OpenAI Whisper
Format conversion to MP4 and web-optimized WebM
Scalable transcription models from 'tiny' to 'large' for speed or accuracy
81 GitHub stars
High-fidelity audio extraction for analysis or standalone use

Use Cases

Generating subtitles and transcripts for recorded lectures or interviews
Converting legacy video formats to universal web standards for deployment
Automating batch processing of media files within a developer workflow

About

Key Features

Support for multiple subtitle formats (SRT, VTT, TXT, JSON)
Automated speech-to-text transcription using OpenAI Whisper
Format conversion to MP4 and web-optimized WebM
Scalable transcription models from 'tiny' to 'large' for speed or accuracy
81 GitHub stars
High-fidelity audio extraction for analysis or standalone use

Use Cases

Generating subtitles and transcripts for recorded lectures or interviews
Converting legacy video formats to universal web standards for deployment
Automating batch processing of media files within a developer workflow