About Lytly
We built Lytly because voice typing should just work.
Lytly started as a personal tool — we needed voice typing that actually understood Hebrew and didn't store our conversations on someone's server. After months of building and testing, we're sharing it.
Technology
Lytly transcribes with a best-in-class large speech model served on specialized fast-inference hardware — accuracy without the wait. Audio is sent only during active recording and deleted immediately. A second provider serves as an automatic fallback, so transcriptions always complete. Provider API keys live on our backend; the desktop app never holds them.
What we stand for
Privacy by design
Your audio is processed in memory and discarded before the HTTP response returns. We don't want your words — we just want to transcribe them.
Speed without compromise
Sub-2-second round-trips, direct paste into any focused app, and adaptive silence detection that stops when you stop — not 3 seconds later.
True multilingual
Eight languages are first-class: English, French, Spanish, German, Hebrew, Russian, Chinese and Japanese. Same hotkey, same UI, same paste flow. No "switch language" menu — it just works.
Roadmap
-
✅
Beta launchWindows + macOS + Linux · Eight languages · Per-call privacy receipts
-
🔄
iOS appThe Lytly keyboard for iPhone — voice typing into any app
-
⬜
Browser extensionVoice typing directly in web apps — no desktop install required
Join us
We're building in public. Follow along, try the app, or reach out directly at hello@lytly.app.