Live captions for any audio
Works with videos, podcasts, meetings, calls, games and more.
Quick answer: Huz Caption Live is a privacy-first Android app that turns speech from any audio into real-time text via a floating overlay. 100% offline processing. Free Pro available
Live captions for any audio on your phone.
Huz Caption Live turns speech into text in real time and shows it as a floating overlay, so you can read captions while using any app. Watch videos without subtitles, follow podcasts, understand meetings and calls, or simply read what's being said — without missing a word.
Huz Caption Live captures the audio playing on your device, runs it through on-device speech recognition, and displays live captions on a movable overlay that floats above every app.
Works with videos, podcasts, meetings, calls, games and more.
Captions appear on top of any app, resizable and movable for convenience.
Your audio is processed entirely on-device. It never leaves your phone.
Support for English, Vietnamese, Chinese, Spanish, French, German, Portuguese, Italian, Hindi, Japanese, Korean, Russian, and more.
"Small & fast", "High accuracy" and "Large" models to balance speed, accuracy and storage.
Captions keep working with a persistent notification for uninterrupted use.
Your audio is processed entirely on your device. Nothing is uploaded or stored in the cloud. Huz Caption Live is built with a privacy-first approach to ensure your conversations and content remain private.
Note: To work, the app needs permissions for screen capture (audio), display over apps (overlay), and notifications.
Take your experience further with Huz Caption Pro. Unlock Live Translation to translate captions into 30+ languages as they appear.
Huz Caption Pro is an optional auto-renewing subscription. You can cancel anytime in Google Play.
Yes, the core features of Huz Caption Live are free. Live translation is available as part of the optional Pro subscription.
Yes, since the overlay floats on top of your screen, it works with any app that plays audio, including YouTube, Zoom, Netflix, and phone calls.
Accuracy depends on the model level you choose ("Small", "High", or "Large") and the clarity of the audio. The "Large" model offers the highest accuracy.
Because it uses on-device AI for speech recognition, it may use more battery than simple apps. Using the "Small & fast" model can help conserve battery.
Download from Google Play today and start reading everything you hear.
Install on Google Play — Free