openai-whisper

Local speech-to-text transcription can be performed directly on your machine using the Whisper CLI. It converts audio files like MP3 or M4A into text format without sending data to an external API or requiring an API key.

Yes, local speech-to-text translation supports translating audio from various languages into English text. The Whisper CLI processes the audio file locally to generate the translated English output.

Yes, local speech-to-text transcription requires the Whisper binary to be installed and configured on your local system. The Skill leverages this CLI tool to process audio files and generate text output.

You can balance speed and accuracy in local speech-to-text transcription by selecting a specific Whisper model. The Skill allows you to choose your model, such as the medium model, to manage the trade-off between processing speed and transcription accuracy.

Local speech-to-text transcription supports various audio formats, including MP3 and M4A. You can specify the path to your audio file and the Whisper CLI will process it to output a text file.

Local speech-to-text transcription is ideal for private voice memos or recorded meetings. Because the audio is processed directly on your local machine, the data remains private without needing to be sent to an external API.