Caption.im — Real-Time AI Captions for Your Mac
What is Caption.IM?
Caption.IM is a privacy-first AI captioning assistant for macOS that converts any system audio into real-time subtitles, translations, and structured meeting notes. It takes audio from any app (video calls, courses, podcasts, livestreams, recorded videos) and outputs live captions, translated subtitles, and AI-generated summaries. The app is developed by INNAIO France and runs on Apple Silicon (M1, M2, M3 and later) with macOS 15.6 or later.
Key Features
- Real-time transcription — Generates live captions for meetings, videos, podcasts, and calls directly from system audio.
- Instant translation — Provides real-time translated subtitles in multiple languages.
- Floating subtitle window — An elegant transparent overlay that works seamlessly with macOS.
- AI meeting summaries — Automatically produces structured summaries, key points, action items, and mind maps after conversations.
- Works with any app — Captures audio from Zoom, Google Meet, Microsoft Teams, YouTube, online courses, podcasts, webinars, and more.
- Privacy-first local AI — All speech recognition and processing runs locally on your device; your conversations never leave your Mac.
- Optimized for Apple Silicon — Architecture designed for ultra-fast speech recognition with minimal latency and efficient power usage.
Who should use Caption.IM?
- Remote workers and multilingual teams — Get real-time captions and translations during virtual meetings across Zoom, Teams, and Google Meet.
- Students and online learners — Capture live subtitles for online courses, lectures, and YouTube videos to improve comprehension and note-taking.
- Accessibility users — Obtain live captions for any audio content on your Mac, enabling hearing-impaired users to follow conversations.
- Content creators and researchers — Record audio and convert long discussions into searchable transcripts and AI-generated summaries.
What can you do with Caption.IM?
- Remote meetings: Generate live subtitles and automatic post-meeting summaries with key insights and action items.
- Online learning: Read real-time captions for lecture videos and online courses, then export structured notes.
- Multilingual collaboration: Instantly translate spoken content into your preferred language using real-time subtitles.
- Accessibility: Use the floating transparent overlay to display captions over any application without blocking content.
How does Caption.IM work?
Install the app, grant system audio access, and it begins capturing audio from whatever app is currently playing. Captions appear in a floating window that you can reposition. No bots or browser extensions required — the app runs entirely on your Mac.
Pricing
Caption.IM is free to download with in-app purchase subscriptions: Pro Monthly (14.99 €), Pro Annually (163.99 €), Premium Monthly (9.99 €), and Premium Annually (108.99 €). Subscriptions automatically renew unless canceled at least 24 hours before the end of the current billing period.
FAQ
Is Caption.IM free?
The app is free to download, but full features require a subscription. Subscription tiers include Pro and Premium options with monthly or annual billing.
Does Caption.IM work on Intel Macs?
No. The app requires macOS 15.6 or later and is optimized exclusively for Apple Silicon (M1, M2, M3 and later).
Can I use Caption.IM without an internet connection?
Yes — all speech recognition and processing runs locally on your device, so the app works offline for transcription and translation. Only optional cloud features (if any) would require connectivity.
Does Caption.IM collect my audio data?
No. The developer states that no data is collected from this app. All processing is done on-device, and your conversations never leave your Mac.
