Super Fast Local Transcribe

Tap once and speak. Words appear as you talk, transcribed on the iPhone itself. No account, no cloud, no subscription. 25 European languages.

Tap one button, speak, and watch your words appear.

SFLT turns speech into text entirely on your iPhone, on the Neural Engine. Nothing is uploaded. There is no account, no subscription and no per-minute bill. You buy it once.

LIVE TEXT, HONESTLY Words arrive while you are still talking. Settled words are solid; the last few seconds are dimmed, because the model may still change its mind about them. When you stop, a final pass over the whole recording produces the transcript that gets saved.

EVERY WORD IS TIMED Audio and transcript are kept together, with a timestamp on every word. Play a recording back and the text follows along. Tap any word to jump to that moment.

SEND IT ANYWHERE Export plain text, SRT subtitles, the M4A audio, or audio and text together, through the normal iOS share sheet: Mail, Messages, Signal, WhatsApp, AirDrop, Files, Shortcuts. No integrations of ours. No server of ours.

A LIBRARY, NOT AN ACCOUNT Every recording is a folder on your phone holding the audio, the transcript and its title. Rename it, share it, delete it. Nothing to sign in to, nothing to sync, nothing to cancel.

25 EUROPEAN LANGUAGES Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian.

NOTHING LEAVES THIS IPHONE The app makes exactly one kind of network request, ever: it downloads the speech model once, during setup. After that it works in airplane mode permanently, which is the easiest way to check the claim yourself. No analytics, no crash reporting, no advertising identifier, no account.

BEFORE YOU BUY iPhone only, portrait, iOS 18 or later. Setup downloads a 467 MB model once, best over Wi-Fi. Transcription is a machine reading your voice, so it makes mistakes; the transcript is a draft, not a record.

Made by Run Labs in Vienna. Speech recognition by Voz from Desert Ant Labs, built on NVIDIA Parakeet TDT 0.6B v3 (CC BY 4.0).