openai-whisper-api

Transcribe single-file audio to text via OpenAI's Whisper API with curl.

202|36|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/adoresever/AGI_Ananas --skill openai-whisper-api-adoresever
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/adoresever/AGI_Ananas/tree/main/26.2.21openclaw-viking/skills/openai-whisper-api
Command: npx skills add https://github.com/adoresever/AGI_Ananas --skill openai-whisper-api-adoresever

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill provides a programmatic way to convert spoken audio into text using OpenAI's Whisper API via curl, enabling automation of transcription tasks without manual typing.

Core Features & Use Cases

  • Transcribing single-file audio inputs to text with optional language and prompt customization.
  • Outputs can be plain text or JSON transcripts for easy downstream processing.
  • Use Case: Automate meeting transcriptions, podcast captioning, or voice memo archiving.

Quick Start

Transcribe an audio file to text using OpenAI’s Whisper API with curl.

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 OpenAI Whisper with curl?

To transcribe audio to text with OpenAI Whisper using curl, you supply a single-file audio input to the Whisper API script. This workflow requires your OPENAI_API_KEY and curl to process the audio file and return plain text or JSON transcripts.

Can I customize language and prompt settings for speech-to-text transcription?

Yes, you can customize language and prompt settings for speech-to-text transcription. The Whisper API workflow allows optional language specification and prompt customization to guide the transcription model, yielding more accurate plain text or JSON outputs.

Does the Whisper API transcription script support multiple audio formats?

The Whisper API transcription script works for single-file audio inputs across languages. It processes your audio file via curl and requires the OPENAI_API_KEY to generate plain text or JSON transcripts for downstream processing.

What's the best way to automate meeting transcriptions and podcast captioning via curl?

The best way to automate meeting transcriptions and podcast captioning via curl is using a scriptable Whisper API workflow. By passing audio files programmatically with your OPENAI_API_KEY, you output plain text or JSON transcripts automatically.

Do I need an OPENAI_API_KEY to run the audio transcription script?

Yes, you need an OPENAI_API_KEY to run the audio transcription script. The curl-based workflow requires this key to authenticate requests to the OpenAI Whisper API, which processes your single-file audio inputs into text transcripts.