Transcribes audio files into text locally using the OpenAI Whisper CLI without requiring an API key.
This skill integrates local speech-to-text capabilities into your workflow by leveraging the OpenAI Whisper CLI. It allows for high-accuracy transcription and translation of various audio formats directly on your machine, ensuring data privacy and eliminating the need for paid cloud-based APIs. By providing standardized CLI patterns, it enables you to quickly generate subtitles, plain text logs, or translated content with customizable model sizes to balance processing speed and transcription precision.
主な機能
010 GitHub stars
02Direct integration with the local system via Homebrew-based installation
03Flexible output formats including TXT and SRT for subtitles
04Support for multiple model sizes to optimize for speed or accuracy
05Local audio-to-text transcription without external API dependencies
06Built-in translation capabilities for multilingual audio sources
ユースケース
01Generating local SRT subtitles for video content without cloud uploads
02Transcribing meeting recordings or voice memos into searchable text files
03Translating foreign language audio files into English text locally
