Caption.IM is a desktop app that provides real-time captions and voice input for any application. It captures system audio from meetings, calls, podcasts, and videos, displaying accurate transcriptions with 98%+ accuracy. Users can translate captions into 50+ languages instantly, with all processing done locally for privacy. It supports speaker detection, global hotkeys, and transcript exports in TXT, SRT, or VTT formats. Ideal for professionals, international teams, and accessibility needs, it works offline and integrates seamlessly with apps like Zoom, Google.