Skip to content
/transcribeOfficial

Transcribe audio and video using OpenAI with optional speaker diarization and clean summaries.

AIOpenAIAudioTranscription· 1 min read

Quick import: Download the .md file and save it to .claude/commands/ (Claude Code), .cursorrules (Cursor), or paste as a system prompt in ChatGPT, Gemini, or any LLM API.

#What it does

The transcribe skill transcribes audio and video files using the OpenAI transcription API. It supports speaker diarization (labeling who said what), produces clean formatted transcripts, and generates concise summaries. It prefers the bundled CLI for deterministic, repeatable runs.

#How to use

bash
$transcribe
Transcribe this audio or video, include speaker labels when possible, and provide a clean summary.

#Capabilities

  • Transcribe audio files (mp3, wav, m4a, and more)
  • Transcribe video files by extracting audio
  • Optional speaker diarization (speaker labels)
  • Clean formatted output with timestamps
  • Concise summary generation
  • Batch transcription for multiple files

#Output format

  • Full transcript with timestamps
  • Speaker labels (when diarization is enabled)
  • Concise summary of key points
  • Structured output for downstream processing

#Environment

  • OPENAI_API_KEY must be set for live API calls

This skill is from the OpenAI Skills Catalog.

OpenAI·
View all skills