C0:DIC
Voice-to-anything. 8 pipelines, your choice.
Push-to-talk voice dictation with 8 transcription backends, 473 domain dictionaries, native text injection on Windows, and a floating bar that snaps to any screen edge.
What it does
Every claim below is backed by working code in the current build.
Push-to-talk on Ctrl+Shift+D
Hold to record, release to transcribe — or tap to toggle, your call.
globalShortcutService registers the OS-level binding. Toggle the press-to-hold ↔ tap-to-toggle behavior in settings.
8 transcription pipelines
Groq Whisper (216× realtime), Google Chirp 3, OpenAI Whisper API, OpenAI Realtime, BetterWispr, Faster-Whisper (CTranslate2), Whisper Cloud, and offline whisper.cpp.
pipelineAccessService.ts enumerates all eight. Switch between them per session — no relaunch, no model download required for the cloud ones.
473 domain dictionaries
Cardiology, anesthesiology, pharma, biotech, architecture, finance, devops, programming — phonetic + fuzzy matched in <0.1ms.
dictionaryTrie.ts is the engine; the 473 .ts files under src/main/services/dictionaries are the data. Memory footprint <30MB even loaded.
Floating bar overlay
A minimal always-on dock that snaps to any screen edge, shows live amplitude, and exposes record / transcribe / chat.
floatingBarRenderer.tsx — separate Electron window, drag-to-snap behavior, persists position across launches.
Native text injection on Windows
SendInput injects transcribed text into Word, Notepad, web forms — anywhere keyboard input works.
injectionService.ts uses koffi to call user32.dll SendInput on Windows. Linux/macOS fall back to clipboard + Ctrl+V via an isolated ClipboardSandbox.
Pipeline leaderboard
Live latency comparison across all eight backends — pick the fastest for your network.
PipelineLeaderboard.tsx renders first-word latency and total transcription time per pipeline, per session.
Custom abbreviations & hotwords
"EKG" → electrocardiogram. Inject medications, procedures, project codes that the model would otherwise miss.
hotwordProcessor.ts + abbreviationExpander.ts run before injection — your custom terms always win.
Audio + visual feedback
Pulse animation while recording, suppressible UI sounds for start/stop, status timer in the toolbar.
UISoundService + TranscriptionStudioToolbar. Mute the chimes if you're in a meeting.
C0:DIC vs Dragon & Whisper CLI
- Eight backends, swap any time
- Built for medical, legal, dev jargon out of the box
- Native Windows injection — no Auto-Type hacks
- Floating bar that stays out of the way