OpenAI Whisper

Transcribe audio files to text using the OpenAI Whisper API.

6|3|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/lordmacu/nexo-rs --skill openai-whisper-lordmacu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: OpenAI Whisper
Source: https://github.com/lordmacu/nexo-rs/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/lordmacu/nexo-rs --skill openai-whisper-lordmacu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The OpenAI Whisper skill solves the challenge of converting audio to text, providing an efficient way to handle audio transcriptions without the need for manual processing.

Core Features & Use Cases

  • Accurate Transcription: Transcribe audio files (≤25 MB) to text with high accuracy.
  • Flexibility: Offers customization with options for models, languages, prompts, and response formats.
  • Use Case: Ideal for applications where quick and accurate transcriptions are essential, such as podcast transcription, lecture note taking, or call log analysis.

Quick Start

Use the OpenAI Whisper skill to transcribe the audio file 'meeting_recording.mp3' with the 'whisper-large-v3' model.

Frequently Asked Questions about OpenAI Whisper

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

FAQPage Schema
How do I transcribe recorded speech to text using the OpenAI Whisper API?

To transcribe recorded speech to text using the OpenAI Whisper API, you submit audio files for batch processing with authentication. The skill converts the audio into text with high accuracy using models like whisper-large-v3.

What audio file size limitations apply when using OpenAI Whisper for speech-to-text conversion?

OpenAI Whisper speech-to-text conversion supports audio files up to 25 MB. This limitation ensures efficient batch transcription of recorded speech, requiring users to split larger files before processing.

Can I customize the language and response format for audio transcription with OpenAI Whisper?

Yes, OpenAI Whisper audio transcription offers customization with options for models, languages, prompts, and response formats. This allows precise transcription output tailored to specific speech-to-text requirements.

Do I need an authentication key to process audio files for transcription?

Yes, an authentication key for the OpenAI Whisper API is required to process audio files. This key enables the system to access the speech-to-text models and convert recorded speech accurately.

What is the best way to automate podcast transcription and call log analysis?

The best way to automate podcast transcription and call log analysis is batch processing recorded speech through the OpenAI Whisper API. It transcribes audio files to text with precision and speed.

Does OpenAI Whisper transcription work for lecture note taking and meeting recordings?

OpenAI Whisper transcription works effectively for lecture note taking and meeting recordings by converting audio to text. It is intended for batch transcription of recorded speech files under 25 MB.