LiveCaptionN – Live Captions

LiveCaptionN turns your Android phone into a real-time speech-to-text captioning and translation tool that floats on top of any other app — live captions, subtitles, and closed captions for videos, calls, meetings, and everyday conversations. It listens through the microphone or the currently playing app's audio, transcribes what it hears word-by-word as you speak, translates it into the language you pick, and paints the result as a draggable caption window on top of whatever you're watching, scrolling, or studying. Perfect for watching foreign-language videos and shows, following along in meetings and calls, language learning practice, or as a hearing-accessibility aid — an on-screen subtitle overlay that works with any app, not just the ones that ship their own captions. Both halves of the pipeline run fully on-device by default: • Streaming Vosk speech recognition — one long-lived recognizer is fed ~100 ms audio chunks continuously, so captions feel instant instead of arriving in 2-second bursts. • Google ML Kit on-device translation — ~59 supported languages, a one-time ~30 MB download per language pair, then cached offline forever. No account required. No server required for the default pipeline. FEATURES • Floating caption overlay that sits on top of any app, with drag-to-move, pinch-resize, pause, minimize, and close controls • Mic or system audio (via MediaProjection) feeding the same low-latency pipeline • Built-in downloader for additional on-device Vosk models: Small (~30 to 80 MB) or Large server-grade (80 MB to 2 GB, lowest error rate) • On-device translation via Google ML Kit, with LibreTranslate as an optional server backend for wider language coverage • Interface language — translate the entire app UI (menus, settings, overlay controls, notifications) into any of 59 languages; models download once, then the whole app works offline in that language • Transcript history, searchable from inside the app • Share or copy saved transcripts as plain text, with safer local history recovery • Guided first-launch setup with permission and model readiness checks before captioning starts • Save and reuse caption presets for common language and display setups • Automatic update notifications via the GitHub Releases API FREE FOREVER, WITH OPTIONAL UPGRADES Every feature above is free, permanently — nothing gets taken away or paywalled. Two optional monthly subscriptions add more on top: • Ad-Free ($1.99/mo) — removes the banner and app-open ads • Pro ($4.99/mo) — includes Ad-Free and unlocks larger server-grade Vosk speech models, additional Google ML Kit translation languages, extra overlay color themes/fonts, reusable Pro presets, and glossary phrase replacements PRIVACY-FIRST LiveCaptionN does not create an account. Speech recognition and translation both run on your phone, and your captions never leave it. The app shows AdMob ads and uses Firebase Crashlytics/Analytics for crash reports and basic feature-usage stats in release builds — see the privacy policy for details. The app only reaches the internet for ads, for downloading Vosk models (from alphacephei.com) and ML Kit translation pairs (from Google's model service) when you ask it to, to check GitHub for new release builds, and — only if you subscribe — to process your subscription through Google Play Billing. If you enable an optional Whisper or LibreTranslate server in settings, traffic goes to the URL you configure and nothing else. REQUIREMENTS • Android 10 (API 29) or newer • Microphone permission (for mic mode) • "Display over other apps" permission (for the floating caption window) • Notification permission (for optional update alerts) LiveCaptionN is fully open source. Every release is built by GitHub Actions from a public commit you can inspect. Issues, feedback, and pull requests are welcome on GitHub.