openai-whisper-api

Transcribe audio files into text using the OpenAI Whisper API.

386k|81.1k|Updated Nov 24, 2025

Search Tags:#whisper #openai #audio transcription #speech-to-text

Ready to run

npx skills add https://github.com/steipete/clawdis --skill openai-whisper-api

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/steipete/clawdis/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/steipete/clawdis --skill openai-whisper-api

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the conversion of audio files to text, eliminating the need for manual transcription and note-taking during meetings or interviews.

Quick Start

Transcribe the audio file 'meeting.m4a' and save the result as 'meeting.txt'.

Core Features & Use Cases

Audio Transcription: Convert speech from audio files into editable text format.

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 files to text using Whisper?▼

Whisper transcribes audio files into text automatically. Provide an audio file (wav, mp3, m4a, or ogg) and an OpenAI API key; the Skill converts speech to editable text using the OpenAI Whisper API with default model whisper-1.

What audio formats does speech-to-text transcription support?▼

Audio transcription supports wav, mp3, m4a, and ogg formats. The Skill accepts diverse audio sources including meetings, lectures, podcasts, and interviews in any of these formats for conversion to text.

Can I transcribe audio in a specific language or get JSON output?▼

Yes. The Skill supports --language to specify the source language and --json to output results in JSON format instead of plain text, alongside --model and --prompt options for customization.

Do I need anything other than curl and an API key to transcribe audio?▼

Audio transcription requires curl for making API requests and an OPENAI_API_KEY for authentication. These are the only dependencies; the Skill handles the rest with default settings or optional parameters.

What's the difference between transcribing to text versus JSON output?▼

Text output (default) saves transcription as plain text suitable for editing and reading. JSON output (--json flag) structures the result with metadata and transcription data, useful for programmatic processing or downstream integrations.