openai-whisper-api

Transcribe audio files into text via the OpenAI Whisper API.

5|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/JansenAnalytics/claudex --skill openai-whisper-api-jansenanalytics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/JansenAnalytics/claudex/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/JansenAnalytics/claudex --skill openai-whisper-api-jansenanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribe audio into text using OpenAI Whisper API, enabling automated transcription workflows without manual typing.

Core Features & Use Cases

  • Transcription via OpenAI Whisper API using curl requests or HTTP clients.
  • Supports model selection (whisper-1) and language options; outputs plain text or JSON transcripts.
  • Use cases include podcast transcripts, meeting recordings, and accessibility captions.

Quick Start

Configure your OPENAI_API_KEY and run the transcription script against an audio file to produce a text 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 files to text using the OpenAI Whisper API?

To transcribe audio to text, call the OpenAI Whisper API endpoint at /v1/audio/transcriptions using a HTTP client like curl and the whisper-1 model. You need to configure your OPENAI_API_KEY and pass the audio file to receive a plain text or JSON transcript.

Can I use curl to automate speech-to-text transcription for my recordings?

Yes, you can use curl to automate speech-to-text transcription by sending POST requests to the OpenAI Whisper API. This allows you to script batch processing of audio files into text transcripts without manual typing or user interface interaction.

Do I need an OpenAI API key to run a speech-to-text script?

Yes, you must configure a valid OPENAI_API_KEY environment variable to authenticate your requests. The speech-to-text script requires this key to access the OpenAI Whisper API endpoint and process your audio files successfully.

What is the best way to generate podcast transcripts in an automated data pipeline?

Automated podcast transcription is best handled by calling the OpenAI Whisper API via curl within your data pipeline. This approach supports on-demand transcription of meeting recordings and audio files, outputting text transcripts directly into your workflow.

Does the OpenAI Whisper API support language selection for audio transcription?

Yes, the OpenAI Whisper API supports model selection with whisper-1 and includes language options for audio transcription. This allows you to specify the spoken language in your request to generate accurate plain text or JSON transcripts.

Why does my curl request to the audio transcriptions endpoint fail?

Requests to the audio transcriptions endpoint fail if the OPENAI_API_KEY is missing or invalid, or if the audio file format is unsupported. Ensure curl is properly configured and the HTTP client authenticates successfully with the OpenAI Whisper API.