openai-whisper

Transcribe local audio files into text and subtitle formats.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/RobbyMo81/assistantrobby --skill openai-whisper-robbymo81
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-whisper
Source: https://github.com/RobbyMo81/assistantrobby/tree/main/skills/openai-whisper
Command: npx skills add https://github.com/RobbyMo81/assistantrobby --skill openai-whisper-robbymo81

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enable private, local speech-to-text conversion so users can transcribe audio without relying on cloud APIs, credentials, or sending sensitive recordings off-device.

Core Features & Use Cases

  • Local CLI transcription: Leverages the Whisper CLI to transcribe audio files on the user's machine.
  • Flexible output formats: Export plain text, subtitles, or translated transcripts for podcasts, meetings, and voice notes.
  • Use Case: Quickly convert meeting recordings or podcast episodes to searchable text and SRT subtitles while keeping data private and avoiding per-minute API costs.

Quick Start

Transcribe an audio file locally by running whisper /path/to/audio.mp3 --model medium --output_format txt --output_dir .

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?

Transcribe audio locally without an API by running the Whisper CLI on your machine. This allows you to convert meeting recordings or podcasts to text offline, ensuring data privacy and avoiding per-minute cloud API costs.

Can I generate subtitles from audio files on my own machine?

Generate subtitles from audio files on your machine by specifying subtitle output formats with the Whisper CLI. You can export SRT subtitles for podcasts and voice notes while keeping sensitive recordings completely off-device.

Do I need the Whisper CLI binary to transcribe meeting recordings?

Yes, transcribing meeting recordings requires the Whisper CLI binary installed and accessible. You also need local model files downloaded to your cache to support model selection and output format flags for offline speech-to-text.

What is the best way to convert podcasts to text without sending data to the cloud?

The best way to convert podcasts to text without cloud services is local CLI transcription. This offline speech-to-text approach keeps audio data private and eliminates the need for credentials or external API integrations.

Does local speech-to-text support single-file translations for voice notes?

Local speech-to-text supports single-file translations for voice notes. By leveraging the Whisper CLI, you can export translated transcripts directly on your device without relying on external cloud processing.