Purpose Caption.IM is a privacy-first AI subtitle assistant for macOS. It converts any audio on your computer into real-time subtitles, translated subtitles, and structured meeting notes. Unlike browser extensions or meeting bots, it processes system audio directly, so it can generate subtitles for sound in any app, such as video calls, online courses, podcasts, livestreams, or videos.
Key Capabilities
- Real-time transcription: Generate real-time subtitles for meetings, videos, podcasts, and calls.
- Instant translation: Understand multilingual content through real-time translated subtitles.
- Floating subtitle window: A transparent overlay window that works seamlessly with macOS.
- AI meeting summaries: Automatically generate structured summaries and key insights after a conversation.
- Compatible with any app: Zoom, Google Meet, Teams, YouTube, online courses, podcasts, and more.
- Privacy-first on-device AI: All speech recognition and processing can run entirely locally on the device, and conversation content never leaves the Mac.
- Designed for Apple Silicon: Optimized for Apple Silicon (M1, M2, M3, and later chips) to deliver ultra-fast speech recognition, low latency, and efficient power consumption.
How to Use After downloading and installing from the App Store, the app works through system audio and can provide subtitles and translation for sound in any app. Specific operating steps, interface navigation, and setup details are not currently provided in the available information.
Use Cases Suitable for remote meetings, online learning, multilingual teams, accessibility assistance, content creators, researchers, and students. It can instantly turn any conversation into searchable, translatable knowledge.
Limitations and Notes The app requires macOS 15.6 or later. Subscriptions automatically renew unless canceled at least 24 hours before the end of the current billing period. The app is free to download and includes in-app purchases. Available information shows the following optional subscription items and prices: Premium monthly subscription 9.99 euros, Pro annual subscription 163.99 euros, Pro monthly subscription 14.99 euros, Premium annual subscription 108.99 euros. The developer states that the app does not collect any data. The developer has not yet stated which accessibility features the app supports. The ratings and review count in the available information are insufficient to display an overview. In the version history, 1.0.1 improved transcription accuracy on April 23: the audio pipeline was rebuilt, using 16 kHz mono Float32 conversion at the source stage.
