Install on Windows
Run the installer, clear the SmartScreen warning, and know where your data lands.
Six tracks, from your first dictation to running the whole pipeline on your own machine. Pick one and start scrolling, or jump straight to what you need.
Install it, grant two permissions, and dictate your first sentence.
Run the installer, clear the SmartScreen warning, and know where your data lands.
Install the package, grant Microphone and Accessibility, and find the app in your menu bar.
Run the AppImage, sort out audio and input group membership, and understand what Linux gives up.
Press Alt+Space, say a sentence, press it again. What the overlay is telling you, and what to do when nothing appears.
Per-context profiles that decide how your words get rewritten before they land.
What a workspace actually holds — four categories of knowledge entries, plus the settings most people never find.
How InkSpoke decides which workspace applies, how tag scoring really works, and why your tag might not be firing.
The presets InkSpoke ships, what each one actually instructs the model to do, and when to write your own instead.
Three separate systems for getting names and jargon right — which one to use, and the inheritance default that trips everyone up.
Hands-free dictation, and turning a spoken phrase into an action.
Start dictating without touching the keyboard. Picking a name, tuning sensitivity, and keeping it from firing at your podcast.
Select some text, describe the change out loud, and let the model rewrite it in place.
The ten things a command can do, how phrases are matched, and the words you are not allowed to use.
One command, many targets: the six slots InkSpoke understands and how spoken values are cleaned up.
Open, focus, hide and close applications — and an honest account of what works on which platform.
The built-in "press" command — key names, modifiers, repeats and sequences, with no setup required.
Run it on your machine, use ours, or bring your own key.
On-device versus cloud, which Whisper build to download, and what GPU acceleration is actually worth.
The zero-setup cloud option: what you get on each plan, how credits work, and what the trial includes.
Connect your own provider account. Which endpoints genuinely work, and where the compatibility limits are.
Rewrite your dictation with a local model, so even the text-cleanup step never leaves your machine.
What stays on your machine, what leaves it, and how to verify the difference yourself.
An honest map of every point where InkSpoke does and does not touch the network — and how to verify it yourself.
Turn on client-side encryption for synced content, save your recovery key, and understand exactly which fields it does and does not cover.
InkSpoke keeps a local record of what you dictated — including a copy of the audio. Here is how to see it, prune it, and wipe it.
What a diagnostic report contains, what is deliberately stripped out of it, and when it helps support.
The settings that matter once InkSpoke is part of your day.
The six bindings you can change, how conflicts are caught, and why there is no hold-to-talk.
Clipboard paste versus simulated typing, why terminals are special, and how to fix an app that will not accept text.
Capture both sides of a call, separate the speakers, and transcribe audio files you already have.
What syncs, what has to be exported by hand, and what simply has to be set up again.
Pair a device directly over the LAN with a QR code, without anything going through the cloud.
Free with platform-hosted voice + text models. Pro unlocks BYOK, on-device models, and unlimited workspaces.