Dictation overlay — listening · live waveform · local whisper
macOS · VOICE CONTROL LAYER
Dictate, format, ask, remember, and dispatch work — from one always-available macOS overlay. Not voice typing. A voice interface to your tools and your agents.
NOT A WINDOW YOU SWITCH TO
Summon the overlay with a hotkey on top of whatever app has focus — your editor, the browser, TextEdit. Speak, and the result lands right where you're working.
ONE INTERFACE
“just get this thought down before I lose it”
pasted into your editor · live preview
Hold Fn, speak. Live preview, then it pastes into the app you're in.
An AI pass cleans punctuation and structure — your meaning untouched.
A persistent conversation — ask, refine, attach context, come back later.
Highlight anything, say what to do, get the result back in place.
IT'S NOT JUST TRANSCRIPTION
RAW SPEECH
dobra zróbmy tak najpierw sprawdź ten plik potem zobacz testy i nie rozwal scope
FORMATTED
Dobra, zróbmy tak: najpierw sprawdź ten plik, potem zobacz testy — i nie rozwal scope.
Punctuation, capitalization, paragraphs, artifacts removed. Meaning kept exactly.
WORKS OVER ANY APP
Highlight text anywhere, say what to do, and the result drops back in its place — no copy, no chat window, no context-switch.
Hey, yeah we can do the call. i think tuesday works but maybe later is better idk, lmk what suits u Talk soon.
Hey, yeah we can do the call. Tuesday works for me, though a later slot would be preferable. Please let me know what suits you. Talk soon.
CONTINUITY
Talk to an agent that stays with your work. Ask, refine, attach files, follow up — and restore a thread when you need it again.
WORKING HISTORY
PERSONALIZATION
Edit the prompts that drive formatting and assistive mode. Your voice. Your rules. Your agent.
Keep my meaning exactly. Short sentences.
Prefer bullet points for lists. Never touch
code blocks. Always keep the original language.
Return only the result, no preamble. Respect
scope — don't expand the task. Be operational.
Match my tone. Output a ready-to-run patch.
AGENT-STACK READY
Native tools and MCP support turn spoken intent into structured input for agent runtimes — a voice control layer for VibeCrafted-style workflows.
Not a tool you open. A layer that sits over everything you already do — and turns talking into doing.
Install from sourceBUILT FOR macOS · APPLE SILICON
A menu-bar tray, a floating overlay, and a settings window that tells you the truth — local-first STT, permissions, and runtime state at a glance.
Dictation overlay — listening · live waveform · local whisper
Menu-bar tray — show agent, history, notes, diagnostics
Shortcuts — one gesture per mode, applies live, no restart
Keys — stored in the macOS Keychain, write-only, never shown back
SETUP · 12-STEP WIZARD, SIX MOVES
First launch to a ready voice runtime — pick a lane, grant permissions, set language, connect a provider, choose hotkeys, check readiness.
— from first launch to a ready voice runtime —
macOS · APPLE SILICON · v0.12.2
$ git clone https://github.com/vetcoders/codescribe.git
$ make install
$ codescribe --version