openai-whisper-api

Transcribe audio files to text or JSON via the OpenAI Whisper API.

1|Updated Jan 28, 2026

Search Tags:#cli #whisper #audio #openai #curl #transcribe

Ready to run

npx skills add https://github.com/Zentin-L/Masterbot --skill openai-whisper-api-zentin-l

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/Zentin-L/Masterbot/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/Zentin-L/Masterbot --skill openai-whisper-api-zentin-l

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Audio transcription is time-consuming and error-prone when done manually. This skill automates turning speech in audio files into searchable text using OpenAI Whisper via a curl request.

Core Features & Use Cases

Transcribes audio files to text using the OpenAI Whisper API
Supports optional language and prompt for improved accuracy
Outputs plain text or JSON transcripts for downstream processing

Quick Start

Run the transcribe.sh 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 running a script that sends your audio file to the OpenAI Whisper API using a curl request. It requires setting your OPENAI_API_KEY and validating the file exists.

Can I specify a language or prompt to improve audio transcription accuracy?▼

Yes, the transcription process supports optional language and prompt parameters to tailor results. Providing these inputs helps the Whisper API generate more accurate transcriptions for your specific audio context.

What audio transcription output formats are supported by this curl script?▼

The curl script outputs transcriptions in either plain text or JSON format. This allows you to seamlessly integrate the resulting transcripts into downstream processing pipelines.

Do I need curl to run this OpenAI Whisper transcription script?▼

Yes, curl is required as a dependency to execute the API request. You must also configure the OPENAI_API_KEY environment variable before running the transcription script.

How do I select a specific Whisper model for transcribing audio files?▼

You can select a specific Whisper model during the transcription process. The script accepts a model parameter, allowing you to tailor the API request to your desired transcription specifications.