openai-whisper-api

Transcribe audio files to text using the OpenAI Whisper API.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/ISAQQSAI/SkillAttack --skill openai-whisper-api-isaqqsai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/ISAQQSAI/SkillAttack/tree/main/data/hot100skills/025_steipete_openai-whisper-api
Command: npx skills add https://github.com/ISAQQSAI/SkillAttack --skill openai-whisper-api-isaqqsai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Converts audio recordings into text using the OpenAI Whisper API, enabling searchable transcripts and accessibility enhancements.

Core Features & Use Cases

  • Transcribe audio to text via the Whisper API using curl with customizable model and output format.
  • Support for language selection and optional prompts for improved transcription.
  • Use cases include podcasts, lectures, interviews, and meeting transcripts for analysis and record-keeping.

Quick Start

Transcribe a local audio file by running the provided transcribe.sh script with the path to the audio 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 Whisper API?

You can transcribe audio to text by running the provided curl command to call the OpenAI Whisper API endpoint at /v1/audio/transcriptions. The script processes your local audio file and returns a text transcript using the specified model and output format.

Can I batch transcribe multiple audio files like podcasts or lectures with Whisper?

Yes, the transcription script supports batch processing for audio files such as podcasts, lectures, and meetings. It applies the same Whisper API parameters across multiple files to produce searchable transcripts for your audio recordings.

What options can I customize when using the OpenAI Whisper API for speech-to-text?

The speech-to-text transcription supports customizable options including model selection, language specification, prompt guidance, and output format. These parameters are passed directly through curl to the Whisper API endpoint.

Do I need an OPENAI_API_KEY to transcribe audio files with curl?

Yes, an OPENAI_API_KEY is required for authentication to access the OpenAI Whisper API. You must provide this key in your curl request headers to successfully transcribe audio files to text.

Does the Whisper API transcription support language selection for non-English audio?

Yes, the transcription process supports language selection options. You can specify the target language when calling the Whisper API via curl to improve transcription accuracy for non-English audio recordings.

What is the best way to generate searchable transcripts from meeting recordings?

The best way to generate searchable transcripts is using the Whisper API to convert meeting audio to text. This process enables accessibility enhancements and searchable text output directly from your local audio files.