openai-whisper

Transcribe local audio files into text using the Whisper CLI.

2|1|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/zhangziliang04/moltbot_deepseek --skill openai-whisper-zhangziliang04
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/zhangziliang04/moltbot_deepseek/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/zhangziliang04/moltbot_deepseek --skill openai-whisper-zhangziliang04

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local Whisper-based transcription enables turning speech into text on-device without API keys, preserving privacy and reducing latency.

Core Features & Use Cases

  • Local CLI transcription with model selection and language support.
  • Works offline on personal machines for private or sensitive audio.
  • Use cases include interviews, lectures, and meeting notes without sending data to the cloud.

Quick Start

Transcribe a local audio file by running whisper on your machine.

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 API keys?

Local audio transcription without API keys is done by running the Whisper CLI on your personal machine. This Skill executes offline speech-to-text transcription directly on your device, ensuring privacy and reducing latency for sensitive audio workflows.

Can I use Whisper for offline transcription of sensitive meeting recordings?

Whisper is suitable for offline transcription of sensitive meeting recordings. It processes audio entirely on your local machine without sending data to the cloud, making it ideal for privacy-sensitive workflows like interviews, lectures, and meeting notes.

How do I select different models and languages for speech-to-text transcription?

Speech-to-text model and language selection is handled through configurable CLI options. You can specify different language settings and model sizes for local transcription as described by the Whisper CLI parameters installed on your machine.

What are the prerequisites for running local audio transcription with Whisper?

Running local audio transcription requires Whisper binaries to be installed on your personal machine. This Skill operates entirely through the CLI, so you need the binary configured locally before executing offline transcription tasks.

Is local Whisper transcription best for small projects or large-scale processing?

Local Whisper transcription is best suited for small projects, personal machines, or privacy-sensitive audio workflows. It processes files on-device, which may limit throughput for large-scale processing compared to cloud-based alternatives.

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

Local speech-to-text transcription preserves privacy by keeping audio data on-device and reduces latency by eliminating network transfers. It is ideal for privacy-sensitive workflows where you cannot send audio files to the cloud.