openai-whisper

To transcribe audio locally without an API, this Skill uses the Whisper CLI to perform speech-to-text conversion directly on your machine. It supports various audio formats and model sizes for flexible, privacy-preserving processing.

Yes, you can translate spoken audio into English text locally using the Whisper CLI. This Skill handles multilingual audio processing and outputs the translated English transcription without relying on external services.

No, you do not need an API key to use this Whisper speech-to-text Skill. It runs entirely locally on your system, ensuring your audio data remains private without requiring external authentication.

The best way to transcribe a long meeting recording locally is using the Whisper CLI with a medium model. This Skill processes the audio file directly on your machine and outputs a text transcription for documentation.

A key limitation of using the Whisper CLI for local audio processing is that it requires the whisper binary to be pre-installed and accessible in your system's PATH before the Skill can execute any transcription or translation tasks.