openai-whisper

Transcribe audio files locally using the Whisper CLI without external APIs.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/Jnuso/OpenClaw --skill openai-whisper-jnuso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/Jnuso/OpenClaw/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/Jnuso/OpenClaw --skill openai-whisper-jnuso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribing audio often depends on cloud services or API keys; this skill enables offline transcription locally using the Whisper CLI, avoiding API keys.

Core Features & Use Cases

  • Local transcription: Convert speech to text on-device without sending data to external services.
  • Language and translation support: Leverage Whisper's models to transcribe or translate audio.
  • Use Case: Transcribe lectures, interviews, or podcasts offline for archiving or note-taking.

Quick Start

Transcribe a given audio file locally using Whisper CLI and save the transcript.

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 offline without using external APIs?

To transcribe audio offline, you can use the Whisper CLI locally on your machine to convert speech to text without relying on cloud services or API keys. This skill enables on-device transcription for recordings, interviews, or lectures.

Do I need an API key to transcribe recordings locally with Whisper?

No, you do not need an API key to transcribe recordings locally with Whisper. The process runs entirely offline using the Whisper CLI binary installed on your host machine, avoiding any external service dependencies.

Can I translate audio to text locally during offline transcription?

Yes, you can translate audio to text locally during offline transcription. The skill leverages Whisper's models to support both transcription and translation tasks without sending your audio data to external services.

What do I need to run local speech-to-text transcription on my machine?

To run local speech-to-text transcription, you need the Whisper CLI binary installed on your host machine. This setup allows you to select specific models and convert speech to text entirely offline.

Is local transcription suitable for archiving podcasts and lectures?

Yes, local transcription is suitable for archiving podcasts and lectures. By using the Whisper CLI offline, you can convert spoken audio into text for note-taking and archiving without requiring internet connectivity.

Can I select different models for offline transcription?

Yes, you can select different models for offline transcription. The skill supports model selection within the Whisper CLI, allowing you to adjust transcription accuracy and performance based on your local hardware capabilities.