transcribe

Transcribe audio files into text using OpenAI's API with optional speaker diarization.

2|Updated Jul 9, 2026
One-click install
npx skills add https://github.com/koki3141/codex-global-skills --skill transcribe-koki3141
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/koki3141/codex-global-skills/tree/main/transcribe
Command: npx skills add https://github.com/koki3141/codex-global-skills --skill transcribe-koki3141

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the transcription of audio files into text, with optional speaker diarization, saving you time and effort in processing audio data.

Core Features & Use Cases

  • Audio Transcription: Convert audio files into text with high accuracy.
  • Speaker Diarization: Label speakers in multi-person conversations.
  • Use Case: Transcribe interviews, meetings, or lectures for easier reference and organization.

Quick Start

Use the transcribe skill to transcribe the audio file 'meeting.mp3' and label speakers using known speaker references.

Frequently Asked Questions about transcribe

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

FAQPage Schema
How do I transcribe an audio file and label multiple speakers?

Audio transcription with speaker diarization converts spoken conversations into formatted text while labeling individual speakers. This process uses OpenAI's API to extract text from audio and applies known speaker hints to identify participants in meetings or interviews.

Do I need an OpenAI API key to extract text from audio files?

Yes, text extraction from audio files requires an OpenAI API key and a Python environment with the openai library installed. The transcription automation sends audio data to OpenAI's API for processing and returns extracted text results.

What's the best way to automate transcription for meeting recordings?

Automating audio transcription for meeting recordings involves submitting audio files to an API-driven workflow that processes content and returns structured text. This approach handles multi-person conversations by applying speaker diarization to label participants throughout the recording.

Can I provide known speaker hints to improve transcription accuracy?

Yes, speaker diarization supports known speaker hints to improve identification accuracy in multi-person audio. Providing reference names for expected speakers helps the transcription engine correctly label dialogue and creates accurate transcripts for interviews.

Does OpenAI transcription support speaker diarization for interviews?

OpenAI API transcription supports optional speaker diarization to label different speakers in interview recordings. This feature identifies and separates individual participants throughout the audio file, producing organized transcripts suitable for reference.