openai-whisper

Transcribe audio files locally to text using the Whisper CLI.

Updated Feb 1, 2026

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

Ready to run

npx skills add https://github.com/NJUxlj/openclaw --skill openai-whisper-njuxlj

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a local, privacy-preserving solution for converting spoken audio into written text, eliminating the need for cloud-based APIs and associated costs or data concerns.

Core Features & Use Cases

Local Transcription: Transcribes audio files directly on your machine using the Whisper CLI.
Multiple Formats: Supports various output formats like plain text (txt) and subtitle files (srt).
Model Selection: Allows choosing different Whisper models (e.g., turbo, medium) to balance speed and accuracy.
Use Case: Transcribe meeting recordings, voice notes, or interviews without uploading sensitive audio to external services.

Quick Start

Use whisper to transcribe the audio file located at /path/to/audio.mp3 using the medium model and output the result as text.

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 files locally without uploading sensitive recordings to external services?▼

Local speech-to-text transcription processes audio files directly on your machine, ensuring data privacy. This approach eliminates cloud-based API requirements and prevents sensitive recordings from leaving your environment.

What output formats can I generate when transcribing voice notes or interviews?▼

Speech-to-text transcription supports various output formats, including plain text files (like txt) and subtitle files (like srt). This allows you to generate transcripts or subtitles directly from your audio recordings.

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

Yes, local speech-to-text transcription requires the Whisper binary to be installed and accessible in your system's PATH. This prerequisite enables the CLI to process audio files locally on your machine.

Can I balance transcription speed and accuracy by changing the speech-to-text model?▼

Yes, local speech-to-text allows you to select different Whisper models, such as turbo or medium. This model selection lets you balance transcription speed and accuracy based on your specific requirements.

Does local transcription work for converting meeting recordings into text?▼

Yes, local speech-to-text transcription is applicable for transcribing meeting recordings, interviews, and voice notes. It converts spoken audio into written text without relying on cloud-based APIs.