openai-whisper

Transcribe audio locally using the Whisper CLI without API keys.

1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/sarathi-aiml/openclaw-zero-trust --skill openai-whisper-sarathi-aiml
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/sarathi-aiml/openclaw-zero-trust/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/sarathi-aiml/openclaw-zero-trust --skill openai-whisper-sarathi-aiml

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local privacy-first speech-to-text: transcribe audio locally using Whisper without requiring an API key or internet access.

Core Features & Use Cases

  • Offline transcription using the Whisper CLI without external calls.
  • Supports multiple models (e.g., medium, large) and outputs (txt, srt).
  • Notes: models download to ~/.cache/whisper; default model may vary by install.

Quick Start

Run whisper on a local audio file with a chosen model to generate a transcription.

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 an API key?

You can transcribe audio locally without an API key by invoking the Whisper CLI, which processes files offline. This approach ensures privacy for note-taking and media analysis by keeping all data on your machine without requiring internet access.

Can I use Whisper for offline speech-to-text transcription?

Yes, Whisper supports offline speech-to-text transcription by utilizing local models cached in ~/.cache/whisper. It performs processing entirely on your machine, making it suitable for private podcast transcription and media analysis where internet access is unavailable.

Do I need the whisper binary installed to transcribe audio files?

Yes, you need the whisper binary and local models installed to transcribe audio files using this method. The required models download automatically to ~/.cache/whisper, enabling offline transcription without external API calls or internet connectivity.

What audio transcription output formats does the Whisper CLI support?

The Whisper CLI supports multiple output formats including txt and srt files for audio transcription. You can select your desired format when running the transcription process, allowing flexibility for note-taking or generating subtitle files.

Which Whisper models can I use for local speech-to-text processing?

Local speech-to-text processing supports multiple Whisper models such as medium and large. The default model may vary depending on your installation, and all models are cached locally in ~/.cache/whisper for subsequent offline transcription tasks.

Why use offline transcription instead of cloud-based speech-to-text services?

Offline transcription provides privacy-first speech-to-text processing by keeping all audio data local without external calls. This approach is ideal for sensitive media analysis and private note-taking where data security and confidentiality are primary concerns.