openai-whisper-api

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

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

327|85|Updated Jan 29, 2026

Search Tags:#OpenAI #Whisper #bash #transcription #audio #curl

Ready to run

npx skills add https://github.com/letta-ai/lettabot --skill openai-whisper-api-letta-ai

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribing audio files into text can be time-consuming and error-prone when done manually. This Skill provides a lightweight curl-powered workflow to leverage OpenAI's Whisper API for fast, automated transcriptions that can be integrated into scripts and pipelines.

Core Features & Use Cases

Curl-based transcription: Use a simple bash script to post audio to OpenAI's Whisper endpoint and receive text or JSON transcripts.
Configurable outputs: Choose the transcription model, language, and output format (text or JSON) to fit your downstream workflows.
Automation-friendly: Ideal for batch-processing recordings, meeting minutes, and media archiving in automated pipelines.

Quick Start

Use {baseDir}/scripts/transcribe.sh with your audio file to generate a transcript. The default model is whisper-1 and the default output is a .txt file next to the input.

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 OpenAI Whisper?▼

You can transcribe audio files into text using OpenAI Whisper by running a simple bash script that posts your audio file to the Whisper API endpoint via curl, returning a text or JSON transcript.

Can I automate audio transcription in bash scripts for batch processing?▼

Yes, you can automate audio transcription in bash scripts for batch processing. This curl-based workflow is designed to be automation-friendly, making it ideal for processing meeting minutes and media archives in automated pipelines.

Do I need an OpenAI API key and curl to use this Whisper transcription workflow?▼

Yes, you need an OpenAI API key and curl to use this Whisper transcription workflow. The script requires curl installed on your system and an OPENAI_API_KEY configured to authenticate the API calls.

What is the best way to configure Whisper transcription outputs like language and format?▼

The best way to configure Whisper transcription outputs is by specifying the desired model, language, and output format. The script defaults to the whisper-1 model and outputs a .txt file next to your input audio.

Why does my curl audio transcription script not return JSON output?▼

Your curl audio transcription script might not return JSON output because the default output format is text. You need to explicitly configure the script to request the JSON output format to receive structured transcript data.