openai-whisper

Transcribe local audio files to text using the Whisper CLI.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/DharambirAgrawal/Personal-Assistant --skill openai-whisper-dharambiragrawal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/DharambirAgrawal/Personal-Assistant/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/DharambirAgrawal/Personal-Assistant --skill openai-whisper-dharambiragrawal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe audio locally without sending data to external APIs, ensuring privacy and reducing latency.

Core Features & Use Cases

  • Offline transcription: Use Whisper CLI to convert speech to text on your machine without network access.
  • Language support: Transcribes and translates audio with multiple models to balance speed and accuracy.
  • Use Case: Personal note-taking, meeting transcripts, or archiving interviews without exposing data externally.

Quick Start

Transcribe a local audio file to text using whisper.

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 locally without sending data to external APIs?

You can transcribe audio locally by using the Whisper CLI to convert speech to text directly on your machine. This approach ensures privacy and reduces latency by operating entirely offline without API keys.

Can I run speech-to-text transcription completely offline?

Yes, you can run speech-to-text transcription completely offline using the Whisper CLI. It converts local audio files to text on your machine without requiring network access, making it suitable for private environments.

Do I need an API key to use Whisper for audio transcription?

No, you do not need an API key to use Whisper for audio transcription. The process runs locally via the Whisper CLI, requiring only the whisper binary to be installed on your system.

How do I balance speed and accuracy when transcribing local audio?

You can balance speed and accuracy when transcribing local audio by selecting different local models within the Whisper CLI. Multiple models are supported to help you adjust transcription and translation output based on your needs.

What is the best way to transcribe interviews and lectures privately?

The best way to transcribe interviews and lectures privately is using local speech-to-text with the Whisper CLI. It processes audio files directly on your machine, archiving audio notes without exposing data externally.

Does offline transcription with Whisper support different output formats?

Yes, offline transcription with Whisper supports different output formats. The Whisper CLI allows local model selection and provides multiple output formats to suit your transcription tasks.