Acerca de
This skill equips Claude Code with comprehensive speech-to-text capabilities, enabling seamless conversion of audio into actionable text data. It supports a wide range of engines, from the privacy-focused, local-first OpenAI Whisper to enterprise-grade cloud services like Google Cloud Speech and Azure. Users can record live audio, process existing files, identify different speakers through diarization, and generate formatted outputs such as SRT subtitles or structured JSON. It is an essential utility for developers and teams looking to automate meeting notes, generate content captions, or integrate voice-to-text workflows directly into their AI-assisted environment.
