Transcribes and translates audio files locally using OpenAI Whisper CLI with support for over 100 languages.
This skill integrates powerful local speech-to-text capabilities into the Claude environment, leveraging the OpenAI Whisper CLI to process audio without external API dependencies. It allows users to transcribe, translate, and summarize audio recordings in over 100 languages—including Chinese and English—directly from their local machine. By running processing locally, it ensures total data privacy and cost-free operation, making it an essential utility for developers and researchers who need fast, reliable transcription and automated summarization of meetings, interviews, or voice notes.
Key Features
01Local speech-to-text processing for maximum privacy and zero API costs
02Smart summarization feature to extract key points from long recordings
035 GitHub stars
04Support for 100+ languages including Chinese, English, Japanese, and Korean
05Automatic translation of foreign language audio into English text
06Wide format support including MP3, M4A, WAV, OGG, FLAC, and WebM
Use Cases
01Transcribing and summarizing meeting recordings or interviews locally
02Translating foreign language audio content into English for documentation
03Automating bulk audio-to-text conversion workflows via the command line
