openai-whisper-api

Transcribe audio files to text using OpenAI's speech-to-text API.

Updated May 7, 2026
One-click install
npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill openai-whisper-api-moodmnky-llc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/MOODMNKY-LLC/mnky-atlas/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill openai-whisper-api-moodmnky-llc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, node, and includes scripts (resource) components.

What problem does it solve?

Manually transcribing audio files is slow, tedious, and prone to human error, especially for long recordings or content with multiple speakers. This Skill automates audio transcription using OpenAI's state-of-the-art speech-to-text models, delivering fast, accurate results without manual effort.

Core Features & Use Cases

  • Multi-model support: Choose from the high-accuracy gpt-4o-transcribe, lightweight gpt-4o-mini-transcribe, speaker diarization-enabled gpt-4o-transcribe-diarize, or the classic whisper-1 model to balance speed, cost, and feature needs.
  • Flexible output formats: Retrieve transcripts as plain text for easy reading or structured JSON for integration into downstream workflows.
  • Real-world use cases: Content creators can transcribe podcast episodes to generate show notes, researchers can convert interview recordings to text for qualitative analysis, and teams can quickly create text records of meeting recordings.

Quick Start

Use the openai-whisper-api skill to transcribe the attached audio file 'team-meeting.m4a' to a plain text transcript saved in the same directory as the original file.

Frequently Asked Questions about openai-whisper-api

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

FAQPage Schema
How do I transcribe audio to text using the OpenAI API?

Audio transcription via the OpenAI API requires sending audio files using curl to the speech-to-text endpoint with a valid OPENAI_API_KEY. This Skill automates those requests, returning accurate text transcripts for content creation, research, or meeting notes.

Does OpenAI speech to text support speaker diarization?

Yes, speaker diarization is supported by selecting the gpt-4o-transcribe-diarize model. This identifies and separates multiple speakers in audio recordings, providing structured transcripts ideal for research interviews and meeting note generation.

Which OpenAI transcription model should I choose for audio files?

Model choice depends on your balance of speed, cost, and features: gpt-4o-transcribe for high accuracy, gpt-4o-mini-transcribe for lightweight processing, gpt-4o-transcribe-diarize for speaker separation, or whisper-1 as a classic baseline.

What do I need to run audio diarization and transcription workflows?

You need a valid OPENAI_API_KEY, curl for making API requests, and node installed. These dependencies allow the scripts to communicate with OpenAI's speech-to-text API and process audio files into text or JSON outputs.

Can I get JSON output from speech to text processing?

Yes, OpenAI speech to text processing supports flexible output formats. You can retrieve transcripts as plain text for easy reading or structured JSON for direct integration into downstream content creation and media captioning workflows.