Transcribes audio and video files locally using the OpenAI Whisper CLI without the need for an API key.
This skill integrates the OpenAI Whisper CLI into the Claude Code environment, enabling high-accuracy, local speech-to-text transcription and translation. By running models locally, it ensures data privacy and eliminates API costs or internet dependencies for audio processing. It supports a wide range of audio formats and can output results in multiple formats like TXT and SRT, making it an essential tool for developers, researchers, and content creators who need to automate audio-to-text workflows directly from their terminal.
Características Principales
01Local speech-to-text transcription without external API dependencies
02Built-in language translation capabilities for non-English audio
030 GitHub stars
04Support for multiple output formats including TXT and SRT
05Automated model downloading and caching for efficient local execution
06Configurable model selection to balance processing speed and accuracy
Casos de Uso
01Developing automated pipelines to convert large batches of audio files into searchable text
02Generating local transcriptions for recorded meetings, interviews, or voice notes
03Creating SRT subtitle files for video content without uploading data to the cloud
