openai-whisper-api

Transcribe audio files to text using OpenAI's Whisper API via curl.

5|Updated Mar 24, 2026
One-click install
npx skills add https://github.com/HikariShine/AgentStudy --skill openai-whisper-api-hikarishine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/HikariShine/AgentStudy/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/HikariShine/AgentStudy --skill openai-whisper-api-hikarishine

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribe audio to text using OpenAI's Whisper API via curl.

Core Features & Use Cases

  • Transcribes audio files using OpenAI's Whisper API via curl.
  • Supports common formats and outputs either plain text or JSON transcripts for downstream workflows.
  • Use case: convert meeting recordings, podcasts, or voice notes into searchable transcripts and captions.

Quick Start

Run the transcribe.sh script with an 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 an audio file to text using OpenAI Whisper?

You can transcribe audio files to text by sending them to the OpenAI Whisper API via curl. The process accepts common audio formats and outputs plain text or JSON transcripts suitable for meetings, podcasts, or voice notes.

Do I need an OpenAI API key to run audio transcription via curl?

Yes, you need an OPENAI_API_KEY set in your environment to use audio transcription via curl. This key authenticates your requests to the OpenAI Whisper API endpoint for generating text transcripts.

Can I specify the language or output format when transcribing audio with Whisper?

Yes, you can specify optional language, model, prompt, and output format parameters when transcribing audio with Whisper. The API request uses default values for the model and endpoint if these options are not provided.

What audio formats are supported for transcription using the Whisper API?

The Whisper API transcription supports common audio formats for converting recordings into searchable transcripts. This allows you to process meetings, podcasts, and voice notes directly via curl commands.

What is the best way to automate converting voice notes to text using curl?

The best way to convert voice notes to text via curl is using a shell script that calls the OpenAI Whisper API. This approach outputs plain text or JSON transcripts for downstream workflows without manual intervention.

Does Whisper transcription via curl require any other dependencies besides curl?

No, OpenAI Whisper transcription via curl only requires the curl command-line tool and a valid OPENAI_API_KEY. It operates through a standalone shell script to generate readable transcripts from your audio files.