openai-whisper

Transcribe audio files to text using the local Whisper CLI.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/nuno7lopes/alisio --skill openai-whisper-nuno7lopes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/nuno7lopes/alisio/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/nuno7lopes/alisio --skill openai-whisper-nuno7lopes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper.

What problem does it solve?

Transcribes audio files to text without the need for an API key, enabling local speech-to-text capabilities.

Core Features & Use Cases

  • Local Speech-to-Text: Converts audio into text using the Whisper CLI.
  • No API Key Required: Accesses local speech-to-text functionality without the need for API keys.
  • Use Case: Transcribe meeting minutes, lectures, or interviews directly from an audio file on your local machine.

Quick Start

Use the 'whisper' command to transcribe audio: whisper /path/to/audio.mp3 --output_format txt

Frequently Asked Questions about openai-whisper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio to text locally without an API key?

Local audio transcription without an API key is done using the Whisper CLI. It processes speech-to-text directly on your machine, allowing you to convert meeting minutes or lectures into text independently.

Can I convert speech to text from a local audio file using the command line?

Yes, you can convert speech to text from a local audio file using the Whisper CLI. Running the 'whisper' command with your audio path transcribes the file directly on your machine.

Do I need an internet connection to use Whisper CLI for speech-to-text?

No internet connection is required because Whisper CLI performs speech-to-text processing locally. It avoids API dependency entirely, enabling on-demand transcription without external network access.

What is the best way to transcribe interviews without relying on external APIs?

The best way to transcribe interviews without external APIs is using local speech-to-text processing. The Whisper CLI transcribes audio files directly on your machine, ensuring data privacy and avoiding API keys.

Are there limitations when using local processing for speech-to-text transcription?

Local speech-to-text processing requires sufficient local hardware resources to run the Whisper CLI. It is limited to the capabilities of the local environment and does not utilize cloud-based API enhancements.