Lven Instant — on-device on desktop
Voice-to-text that runs entirely on your machine.
Lven started as a question about friction: why does voice input require so many steps? Open an app, record, wait, copy, switch windows, paste. Six steps for something that should be one.
The answer is a floating bubble. It sits on your screen, appears when you are in a text field, and disappears when you are not. Tap it, speak, and the text lands at your cursor with no manual copy, paste, or app switching.
Lven Instant takes that idea and removes the next compromise: privacy. Every word you dictate is converted to text by a quantised speech model downloaded during setup and run on your CPU. No audio upload, no inference round trip. The audio physically does not leave your device.
The engine can transcribe locally without a connection, but the product still validates a cached entitlement and periodically refreshes account credentials. Those account requests contain no microphone audio or transcript text; a device without a valid cached entitlement can require a connection before recording is enabled.
Three tiers: 6 months at $29, 1 year at $49, or a one-time $139 lifetime. One subscription covers every platform as it ships — Windows, Linux, and Android today, with macOS and iPhone on the way. The server-side product, Lven Cloud, is available at /releases/lven/cloud for users who want the highest-accuracy cloud engine.