openai-whisper

Transcribe and translate audio files locally with the Whisper CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/xxrenzhe/autobb --skill openai-whisper-xxrenzhe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/xxrenzhe/autobb/tree/main/openclaw-prebuilt/skills/openai-whisper
Command: npx skills add https://github.com/xxrenzhe/autobb --skill openai-whisper-xxrenzhe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a local, privacy-focused solution for converting spoken audio into written text without relying on external APIs or requiring API keys.

Core Features & Use Cases

  • Local Transcription: Transcribe audio files directly on your machine using the Whisper CLI.
  • Translation: Translate audio from various languages into English.
  • Use Case: You have a confidential meeting recording and need a transcript for documentation, but you cannot send the audio to a cloud service. Use this Skill to generate the transcript locally.

Quick Start

Use the whisper command to transcribe the audio file '/path/to/meeting.mp3' into a text file.

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 files locally without sending data to a cloud API?

Local speech-to-text transcription can be performed directly on your machine using the Whisper CLI, ensuring audio data remains private without relying on external APIs or API keys.

Can I translate spoken audio from another language into English locally?

Yes, local translation of spoken audio from various languages into English is supported, allowing you to process multilingual meeting recordings directly on your machine without uploading files.

Do I need an internet connection or API keys to use local speech-to-text?

No internet connection or API keys are required for local transcription. The process runs entirely offline using the Whisper binary installed directly on your system.

How do I get started with transcribing a meeting recording using Whisper?

To transcribe a meeting recording, use the whisper command with your audio file path, such as '/path/to/meeting.mp3', to generate a text transcript locally on your machine.

What are the limitations of using local speech-to-text for audio transcription?

Local speech-to-text requires the 'whisper' binary to be installed and available in your system's PATH, meaning transcription performance depends entirely on your local hardware capabilities.