transcription

Name: transcription
Availability: InStock
Author: MadAppGang

Transcribe audio and video with OpenAI Whisper into SRT, VTT, and JSON formats.

7|4|Updated Feb 26, 2026

Search Tags:#video #subtitles #transcription #whisper #audio #srt #vtt

Ready to run

npx skills add https://github.com/MadAppGang/magus --skill transcription-madappgang

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: transcription
Source: https://github.com/MadAppGang/magus/tree/main/plugins/video-editing/skills/transcription
Command: npx skills add https://github.com/MadAppGang/magus --skill transcription-madappgang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai-whisper, pyannote.audio, ffmpeg-python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of converting spoken words in audio or video files into written text, making media content searchable, editable, and accessible.

Core Features & Use Cases

High-Accuracy Transcription: Utilizes OpenAI Whisper for reliable transcription.
Multiple Output Formats: Generates transcripts in SRT, VTT, and JSON formats.
Speaker Diarization: Identifies and labels different speakers in the audio.
Use Case: Transcribe a lecture video to create searchable notes or generate subtitles for a YouTube video.

Quick Start

Use the transcription skill to transcribe the attached audio file 'meeting.mp3' and output the result as an SRT file.

Frequently Asked Questions about transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe audio and video files into text with accurate timing?▼

Transcribe audio and video files into text using OpenAI Whisper, which provides reliable speech-to-text conversion with detailed timing information for precise synchronization.

Can I generate SRT and VTT subtitles from a video automatically?▼

Generate SRT and VTT subtitles from video automatically using Whisper transcription, outputting structured subtitle files with accurate timestamps for direct media playback integration.

Does speaker diarization work with OpenAI Whisper for multi-speaker audio?▼

Speaker diarization works with OpenAI Whisper by integrating pyannote.audio, identifying and labeling different speakers in multi-speaker audio files for clear transcript attribution.

Do I need ffmpeg to extract audio for transcription processing?▼

You need ffmpeg to extract audio from video files for transcription processing, ensuring the media is properly formatted for Whisper to accurately parse the speech content.

What's the best way to optimize transcription quality for large audio files?▼

Optimize transcription quality for large audio files by selecting the appropriate Whisper model size based on accuracy needs, applying quality optimization techniques during processing.

How does Whisper model selection affect transcription speed and accuracy?▼

Whisper model selection affects transcription speed and accuracy by balancing processing time against precision, allowing you to choose smaller models for speed or larger models for accuracy.