openai-whisper-api

Name: openai-whisper-api
Availability: InStock
Author: pablomat555

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

1|Updated Mar 9, 2026

Search Tags:#api #transcription #whisper #audio #openai #curl #speech-to-text

Ready to run

npx skills add https://github.com/pablomat555/eggent-ai --skill openai-whisper-api-pablomat555

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/pablomat555/eggent-ai/tree/main/bundled-skills/openai-whisper-api
Command: npx skills add https://github.com/pablomat555/eggent-ai --skill openai-whisper-api-pablomat555

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribing audio manually is slow and error-prone; this skill automates speech-to-text conversion using OpenAI's Whisper API, enabling faster, more accurate transcripts for research, content creation, and accessibility.

Core Features & Use Cases

Transcribes audio files into text via the Whisper API, with a simple script interface.
Supports optional language and prompt parameters to improve accuracy for multilingual or domain-specific content.
Use cases include turning interviews, lectures, podcasts, and customer calls into searchable transcripts for indexing, analysis, and archiving.

Quick Start

Run {baseDir}/scripts/transcribe.sh /path/to/audio.m4a after setting OPENAI_API_KEY.

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?▼

To transcribe audio to text, this skill uses a curl script to post your audio file to the OpenAI Whisper API endpoint at /v1/audio/transcriptions, returning your speech content as searchable text.

Can I use curl to automate speech-to-text conversion for interviews and podcasts?▼

Yes, you can automate speech-to-text conversion for interviews and podcasts by running the provided transcribe.sh script with curl, which sends your audio files directly to the Whisper API for rapid transcription.

Do I need an OpenAI API key to convert audio files into text?▼

Yes, you must set a valid OPENAI_API_KEY environment variable before running the transcription script, as it is required to authenticate your curl requests to the OpenAI Whisper API endpoint.

How can I improve speech-to-text accuracy for multilingual audio transcription?▼

You can improve multilingual speech-to-text accuracy by passing optional language and prompt parameters in your curl request to the Whisper API, helping it handle domain-specific or non-English audio content.

What audio formats can I send to the OpenAI Whisper API for transcription?▼

You can send common audio formats like m4a to the Whisper API for transcription, posting them via curl to the /v1/audio/transcriptions endpoint to convert your lectures or meetings into text.

Is there a simple way to script audio transcription without writing complex code?▼

Yes, running the transcribe.sh shell script with curl provides a simple command-line interface to send audio files to OpenAI Whisper, converting speech to text without needing complex application code.