openai-whisper

Overview: Whisper is a local speech-to-text tool using the Whisper CLI, allowing you to transcribe audio files without requiring an API key. This skill enables you to leverage Whisper’s capabilities from your terminal or command line interface (CLI).

Key Features:

• Transcribe audio files using the Whisper CLI
• Supports various audio formats (e.g., MP3, M4A)
• Offers multiple model options for speed and accuracy
• No API key required

How It Works: This skill utilizes the Whisper CLI to transcribe audio files locally. You can specify the model, output format, and output directory to suit your needs.

Use Cases:

• Transcribe podcasts or lectures for easier consumption
• Convert audio files to text for accessibility purposes
• Use Whisper’s translation capabilities to transcribe audio in multiple languages