openai-whisper-api

Transcribe audio files into text using the OpenAI Whisper API.

2|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/moshehbenavraham/crocbot --skill openai-whisper-api-moshehbenavraham
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/moshehbenavraham/crocbot/tree/main/skills/openai-whisper-api
Command: npx skills add https://github.com/moshehbenavraham/crocbot --skill openai-whisper-api-moshehbenavraham

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribe audio into text using OpenAI Whisper's transcription API, enabling quick conversion of audio content to readable transcripts for search, indexing, and accessibility.

Core Features & Use Cases

  • Transcription with Whisper model selection (default whisper-1) and support for language and prompt hints.
  • Output to text or JSON files, with easy CLI-based workflow integrated into crocbot.
  • Use Case: Convert podcasts, interviews, and meeting recordings into searchable transcripts for archiving and note-taking.

Quick Start

Run the transcribe script on an audio file to produce 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 files into text using the OpenAI Whisper API?

To transcribe audio files into text using the OpenAI Whisper API, you run a curl-based script that uploads your audio and saves the output as text or JSON. You must provide your OPENAI_API_KEY to authenticate the transcription request.

What is the best way to generate searchable transcripts for podcasts and meeting recordings?

Generating searchable transcripts for podcasts and meeting recordings is best handled by passing the audio files through the Whisper transcription API. The script processes the audio input and outputs a readable text file, enabling quick search, indexing, and archiving.

Do I need curl to use the OpenAI Whisper transcription script?

Yes, you need curl to use the OpenAI Whisper transcription script, as it is the sole dependency for executing the API requests. The command-line interface workflow relies entirely on curl to upload audio files and retrieve the transcribed text or JSON output.

Can I specify a language or model when transcribing audio with Whisper?

You can specify a language and model when transcribing audio with Whisper by using the provided prompt hints. The script defaults to the whisper-1 model but supports parameter adjustments to tailor the transcription output to your specific audio context.

Does the Whisper transcription script support JSON output formats?

Yes, the Whisper transcription script supports JSON output formats alongside standard text files. When you run the curl command, you can configure the script to save the resulting transcription as a structured JSON file for easier integration into downstream applications.

Why does audio transcription with Whisper require an OPENAI_API_KEY?

Audio transcription with Whisper requires an OPENAI_API_KEY to authenticate your access to the cloud-based transcription API. The curl script securely sends this key with your audio upload to process the file and return the transcribed text or JSON output.