super-stt

System-wide speech-to-text for Linux that types dictated words into whatever app is focused

Desktopfree

Super STT is an open-source Linux tool that types dictated speech directly into whatever application is focused, triggered by a single keyboard shortcut. A background daemon keeps a chosen speech model warm, supporting local models like Whisper, Voxtral, and Qwen3-ASR as well as cloud providers, and exposes an open local protocol other apps can build on. It targets Linux users who want universal, low-friction voice dictation.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of super-stt - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim super-stt to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether super-stt (or something else) actually fits.

Try a problem