audio-transcribe

Official

Turn audio/video into precise, timed transcripts.

Authormaxgent-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Transcribing audio and video content can be tedious and error-prone; this skill automates the process by using WhisperX to convert speech into text with word-level timestamps, saving time and improving accessibility.

Core Features & Use Cases

  • Multilingual speech recognition with word-level timestamps.
  • Flexible input/output: supports common audio and video formats and outputs in TXT, SRT, VTT, or JSON.
  • Practical use cases include meeting minutes, video captions, podcast transcripts, and archival keyword search.

Quick Start

Run the transcribe.py script on your file to generate a transcript with your preferred options.

Dependency Matrix

Required Modules

torch==2.3.1torchaudio==2.3.1whisperx==3.3.1pyannote.audio==3.3.2transformers==4.44.0matplotlib

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: audio-transcribe
Download link: https://github.com/maxgent-ai/maxgent-plugin/archive/main.zip#audio-transcribe

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.