openai-whisper-api

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

Transcribe audio files via OpenAI's Whisper API endpoint.

2.8k|332|Updated Jan 29, 2026

Search Tags:#api #bash #transcription #whisper #audio #openai

Ready to run

npx skills add https://github.com/moltis-org/moltis --skill openai-whisper-api-moltis-org

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper-api
Source: https://github.com/moltis-org/moltis/tree/main/crates/skills/src/assets/audio/openai-whisper-api
Command: npx skills add https://github.com/moltis-org/moltis --skill openai-whisper-api-moltis-org

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Transcribe audio files using OpenAI’s Whisper API via the /v1/audio/transcriptions endpoint. Configure OPENAI_API_KEY and OPENAI_BASE_URL to enable authentication and routing through a proxy or local gateway.

Core Features & Use Cases

Transcribes audio with the OpenAI Whisper endpoint to generate text transcripts from various audio inputs.
Supports configuring model (e.g., whisper-1), language, and optional prompts to influence transcription results.
Use Case: Automate transcription of interviews, podcasts, or meeting recordings for searchable archives and summaries.

Quick Start

Run the transcription script against an 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 files using the OpenAI Whisper API in a bash pipeline?▼

Transcribe audio files using the OpenAI Whisper API by calling the /v1/audio/transcriptions endpoint via a bash script. You provide an audio file as input and receive a text transcript, which is ideal for automating transcription workflows in developer pipelines.

Do I need curl to use the OpenAI Whisper API for audio transcription?▼

Yes, you need curl to execute the OpenAI Whisper API transcription requests from your bash environment. The script leverages curl to send audio files to the /v1/audio/transcriptions endpoint and retrieve the generated text.

Can I configure a custom proxy or local gateway for OpenAI audio transcriptions?▼

Yes, you can configure a custom proxy or local gateway for OpenAI audio transcriptions by setting the OPENAI_BASE_URL environment variable. Combined with the OPENAI_API_KEY, this routes your API requests through your desired network endpoint.

What is the best way to automate podcast or interview transcription using the Whisper API?▼

Automate podcast or interview transcription by running a bash script that sends audio files to the OpenAI Whisper API. You can configure the model, language, and optional prompts to influence transcription results for searchable archives and summaries.

Does the Whisper API transcription script support specifying languages and optional prompts?▼

Yes, the Whisper API transcription script supports specifying the transcription model, language, and optional prompts. Configuring these parameters allows you to influence the transcription results for various audio inputs.