Caption.IM

Caption.IM is a desktop captioning app built around a simple idea: whatever audio is playing on your machine, you should be able to read it and understand it in your language. It captures system audio directly from your device's output, so it works at the operating-system level with Zoom, Google Meet, Microsoft Teams, Webex, Slack Huddles, Discord and any other app that produces sound. There is no browser extension to install and no per-app configuration.

The app combines two capabilities. First, real-time transcription, which renders speech as on-screen text with high reported accuracy. Second, instant translation into dozens of languages, which makes it useful for international meetings, foreign-language lectures and cross-border calls. Caption.IM states that all audio processing runs locally using optimized AI models, so audio never leaves the device, and it also functions offline.

Beyond live use, Caption.IM works as a voice input method, letting you dictate text into any application through the same engine. Captions can be exported as TXT, SRT or VTT for subtitles, meeting notes or archives, and speaker detection labels who said what. Global hotkeys start and stop captioning instantly.