openai-whisper-api

Transcribe audio files to text using the OpenAI Whisper API.

4|1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/adamhjouj/shieldclaw --skill openai-whisper-api-adamhjouj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/adamhjouj/shieldclaw/tree/main/openclaw/skills/openai-whisper-api
Command: npx skills add https://github.com/adamhjouj/shieldclaw --skill openai-whisper-api-adamhjouj

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribe audio files to text using OpenAI's Whisper API via a simple curl-based workflow.

Core Features & Use Cases

  • Transcription via /v1/audio/transcriptions with configurable model and language.
  • Local, script-based execution using OPENAI_API_KEY for authentication.
  • Use case: convert interviews, lectures, or podcasts into searchable transcripts.

Quick Start

Run the transcribe script with your audio file to generate a transcript.

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 Whisper API?

You can transcribe audio to text by sending a request to the OpenAI Whisper API /v1/audio/transcriptions endpoint with your audio file and OPENAI_API_KEY. This script uses curl to convert recordings like interviews or podcasts into searchable text transcripts.

Can I use curl to transcribe audio files with Whisper?

Yes, you can use curl to transcribe audio files with Whisper by sending a POST request to the /v1/audio/transcriptions endpoint. The script requires the curl dependency and an OPENAI_API_KEY for authentication to process the audio input.

What audio formats and parameters does the OpenAI transcription API support?

The OpenAI transcription API supports optional language, model, and output format parameters sent via curl. You configure these parameters in your request to the /v1/audio/transcriptions endpoint to control how your audio recordings are converted into text.

Do I need an OPENAI_API_KEY to convert audio recordings into searchable transcripts?

Yes, you need an OPENAI_API_KEY to authenticate your requests when converting audio recordings into searchable transcripts. The script uses this key to access the OpenAI Whisper API and process your local audio files via curl.

What is the best way to transcribe lectures or podcasts locally?

The best way to transcribe lectures or podcasts locally is using a script-based curl workflow that calls the OpenAI Whisper API. This approach processes your audio files through the /v1/audio/transcriptions endpoint to generate searchable text transcripts.

Does the Whisper API transcription script support configurable models and languages?

Yes, the Whisper API transcription script supports configurable model and language options. When you run the curl command against the /v1/audio/transcriptions endpoint, you can specify these parameters to tailor the audio transcription output to your needs.