openai-whisper

Local speech-to-text transcription can be performed directly on your machine using the Whisper CLI. This approach processes audio files like MP3 and M4A without relying on external APIs or requiring an API key, ensuring privacy.

Yes, translation of audio from various languages into English text is supported. By running the Whisper model locally, you can convert spoken foreign language audio files into written English documents.

No, you do not need an API key to run speech-to-text processing. The Skill executes the Whisper binary locally, which requires the binary to be installed and configured on your machine for local model execution.

Local Whisper transcription works with common audio file formats such as MP3 and M4A. You can specify a path to your audio file and use the CLI to output the transcription as a text file.

To transcribe a recorded meeting, direct the Whisper CLI to transcribe the audio file located at your specified path using the medium model. The system will process the audio locally and output the transcription as a text file.

The best way to search and reference podcast content is local speech-to-text transcription. By converting spoken podcast audio into a text document using Whisper, you can easily search through the transcribed material for specific references.