InstanTrans

Turn nearby speech, or audio playing in another app, into live translated captions. Keep them in Picture in Picture. Recognition and translation stay on this iPhone.

InstanTrans turns what this iPhone hears into live captions, then translates them into the language you choose. Listen to people nearby, or capture audio playing in another app after you start a system broadcast. Captions can stay in Picture in Picture and float over whatever is on screen.

Use it for a video in another language, a podcast, a meeting, or a conversation in front of you.

Features • Two sources: the microphone, or screen audio • Picture in Picture captions, with type size, font, color, window layout, and text backing you can adjust • Show the recognized original before the translation • History keeps the latest 80 lines. Copy both languages, translate a line again, or export SRT • Optional iCloud sync for caption preferences and history • On-device enhanced recognition (Whisper) when a language has no on-device system speech. The model downloads on first use

How to use

1. Choose the language to listen to, and the language to write
2. Choose the microphone or screen audio
3. Tap play. For screen audio, confirm the system broadcast
4. Turn on Picture in Picture and leave the captions in the floating window

Privacy Recognition and translation run on this device. We do not operate a speech server. Screen audio is captured only after you start a system broadcast. Caption history stays on this device until you clear it, unless you turn on iCloud Sync. With sync on, history and preferences go to your iCloud.

Notes Languages depend on system speech recognition and translation. Some languages download a pack or a local model the first time you use them. If a language has no on-device recognizer, system recognition may need a network connection. Quality depends on those models. Some apps block system audio capture; switch to the microphone when that happens.

Requires iOS 18 or later. Available on iPhone and iPad.