I am building a local Windows dictation tool that turns spoken input into pasted text with global hotkeys, private transcription, and a tightening QA loop.
Overview
SpeakFree is a practical local dictation build. The point is to press a hotkey, speak naturally, and get text inserted where the cursor already is without routing the whole workflow through a cloud transcription product.
What is working now
A Windows desktop shell built in Tauri
Hold-to-talk and toggle dictation modes with global hotkeys
Local transcription through a faster-whisper worker
Clipboard-safe paste into the active app
Persisted microphone selection and phrase hints for tricky terms
A stronger CPU-first transcription profile based on real QA outcomes
Why it matters
It turns dictation quality into something observable and improvable instead of abstract
It is a useful example of desktop product shaping, model tradeoff decisions, and human-in-the-loop QA
It shows how an internal personal tool can become a cleaner public-facing build without pretending it is already a finished SaaS product
Why this belongs in Projects
This is current systems work: product framing, desktop implementation, local AI integration, and visible quality iteration all happening in one build.
