openai-whisper-api

Transcribe audio files into text using the OpenAI Audio Transcriptions API.

4|2|Updated Feb 26, 2026

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

Ready to run

npx skills add https://github.com/Clawdi-AI/openclaw --skill openai-whisper-api-clawdi-ai

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the transcription of audio files into text, making spoken content searchable and editable.

Core Features & Use Cases

Audio Transcription: Converts various audio formats (e.g., M4A, OGG) into text using OpenAI's Whisper API.
Customization: Allows specifying the model, output file path, language, and providing prompts for better accuracy.
Use Case: Transcribe meeting recordings, voice notes, or podcast segments into text for easy searching, summarization, or documentation.

Quick Start

Use the openai-whisper-api skill to transcribe the audio file '/path/to/audio.m4a'.

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 to text using the OpenAI Whisper API?▼

The OpenAI Whisper API transcribes audio files to text by sending audio formats like M4A or OGG to the endpoint, requiring an OPENAI_API_KEY environment variable and curl to execute the request and return text.

Do I need curl and an OpenAI API key to convert speech to text?▼

Yes, converting speech to text requires curl and an OPENAI_API_KEY environment variable. These dependencies authenticate and execute the transcription requests against the OpenAI Audio Transcriptions API endpoint.

Can I customize the language and output format when transcribing audio?▼

You can customize the language and output format when transcribing audio by specifying the model, output file path, target language, and providing prompts to improve accuracy for specific spoken content.

What audio formats are supported for speech-to-text conversion?▼

Supported audio formats for speech-to-text conversion include M4A and OGG. The OpenAI Audio Transcriptions API processes these various audio files to produce editable and searchable text outputs.

What is the best way to transcribe meeting recordings and voice notes?▼

The best way to transcribe meeting recordings and voice notes is using an automated speech-to-text API. It converts spoken content into text for easy searching, summarization, or documentation without manual effort.

Why use prompts when converting audio to text?▼

Using prompts when converting audio to text improves transcription accuracy by providing context. This helps the speech-to-text model correctly interpret specific vocabulary, names, or accents present in the audio file.