openai-whisper

Local speech-to-text transcription without an API key is achieved by using the Whisper CLI directly on your machine. This Skill runs offline to ensure privacy, bypassing external APIs entirely.

Yes, you can translate audio from various languages into English offline. The local transcription mechanism uses the Whisper CLI to process audio files and generate English text output without needing an internet connection.

Yes, you need the Whisper executable installed and available in your system's PATH to use local transcription. This environment setup is required because the Skill acts as a wrapper for the Whisper CLI.

You can transcribe various audio formats using the Whisper CLI. The local speech-to-text processing supports multiple file types, allowing you to directly convert audio recordings into text files.

Choosing a Whisper model size for speech-to-text involves a trade-off between speed and accuracy. You can specify different model sizes when running the local transcription to balance processing time with output quality.

The best way to transcribe a meeting recording offline is using the local Whisper CLI. It converts your audio files into text documents for easy reference and searching without relying on external APIs.