openai-whisper

Name: openai-whisper
Availability: InStock
Author: lllooollpp

Transcribe local audio files to text using the Whisper CLI.

39|10|Updated Jan 27, 2026

Search Tags:#cli #transcription #whisper #audio #local #speech-to-text

Ready to run

npx skills add https://github.com/lllooollpp/clawdbot-cn --skill openai-whisper-lllooollpp

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/lllooollpp/clawdbot-cn/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/lllooollpp/clawdbot-cn --skill openai-whisper-lllooollpp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill allows you to transcribe audio files into text directly on your local machine, without needing to send data to an external API or requiring an API key.

Core Features & Use Cases

Local Transcription: Converts audio files (MP3, M4A, etc.) into text.
Model Selection: Supports various Whisper models (turbo, medium, etc.) for balancing speed and accuracy.
Format Output: Can output transcribed text in formats like .txt or .srt.
Use Case: Transcribe a meeting recording or a voice memo into a text document for easy searching and editing.

Quick Start

Use whisper to transcribe the audio file located at /path/to/audio.mp3 using the medium model and save the output as 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 to text locally without an API key?▼

You can transcribe audio to text locally by using the Whisper CLI to process files directly on your machine, completely bypassing the need for an external API key. This ensures privacy-sensitive audio processing and offline transcription without sending data externally.

How do I convert an MP3 file to SRT subtitles using Whisper?▼

To convert an MP3 file to SRT subtitles using Whisper, you simply run the Whisper CLI on your audio file and specify the output format. The Skill supports outputting transcribed text in formats like .txt or .srt for easy searching and editing.

Does local speech-to-text transcription work offline?▼

Yes, local speech-to-text transcription works entirely offline. By running the Whisper binary directly on your machine, the process handles privacy-sensitive audio processing without needing an active internet connection or sending data to external servers.

Do I need to install the Whisper binary before transcribing audio?▼

Yes, you need to install the Whisper binary before transcribing audio. The Skill requires the Whisper binary to be installed and accessible in your system's PATH to successfully execute local speech-to-text transcription.

Which Whisper model is best for balancing transcription speed and accuracy?▼

To balance transcription speed and accuracy, you can select from various Whisper models like turbo or medium. The Skill supports model selection, allowing you to adjust the local speech-to-text processing based on your specific speed and accuracy requirements.

What audio formats can I transcribe using the Whisper CLI?▼

You can transcribe common audio formats like MP3 and M4A using the Whisper CLI. The Skill performs local speech-to-text transcription on these files and outputs the resulting text in formats such as .txt or .srt.