openai-whisper

Local audio transcription without an API key is achieved by running the Whisper CLI directly on your machine. This Skill operates offline, allowing you to generate text transcripts while preserving privacy and maintaining full control over your data.

Offline transcription for podcasts, lectures, and interviews is fully supported. The Skill processes these audio types locally through the Whisper binary, producing text transcripts without sending your media files to external servers.

Yes, the whisper binary must be installed on your system to use this Skill. It relies on the local Whisper CLI to perform speech-to-text processing rather than calling a cloud-based API.

Audio transcription model selection and language options are configured directly via the Whisper CLI. This Skill passes these parameters to the local binary, enabling you to choose specific models and handle different languages for your transcripts.

The best way to ensure privacy during speech-to-text processing is to run transcription entirely offline. This Skill executes locally without external APIs, guaranteeing your audio data never leaves your device.

Local transcription with the Whisper CLI does not require an internet connection once the binary and models are set up. The Skill operates offline by default, ensuring your audio data remains completely private.