Caption.IM – AI-powered local captions and voice input for Mac

Summary: Caption.IM provides real-time AI-generated captions and translations for any audio on macOS, working across all applications without sending data to the cloud. It offers a floating subtitle window optimized for Apple Silicon, ensuring low latency and local processing for privacy.

What it does

Caption.IM captures audio from any app on your Mac and displays instant, accurate subtitles and translations in a transparent, floating window. It processes audio locally using on-device AI models to maintain privacy and performance.

Who it's for

It is designed for macOS users who need real-time captions and translations during meetings, videos, calls, podcasts, and online courses.

Why it matters

It solves the problem of missing or slow subtitles and avoids cloud-based audio processing, enabling immediate, private, and accessible captions across all desktop content.