Product tour

See how voice becomes text in your desktop workflow.

Follow the first AIspeaky loop: check your desktop setup, dictate one phrase, insert it into an app, then explore translation and supported commands where available.

aispeaky · live preview
Check your desktop setup
Dictation: verified · Insertion: verified · Command mode: gated (per app)
Verified
Press, speak, release
Schedule a quick sync tomorrow at ten.
Verified
Drop it into the app you were already using
Subject: Quick sync tomorrow at ten
Verified
Replayable, no account needed~60s
The first loop

Five steps, in the order you will hit them

1 · Compatibility
Check your desktop setup
First step

We detect OS, desktop session, input method and audio stack, then tell you what works on this machine before you install anything.

Input
Distro: Ubuntu 24.04 · Session: Wayland · Mic: pipewire
Result
Dictation: verified · Insertion: verified · Command mode: gated (per app)

Synthetic report. Your own run lives on /compatibility.

2 · Dictate
Press, speak, release
Local lane

Hold the shortcut, say one phrase, release. Recognition runs on-device by default — no account, no upload.

Input
[hold Super+Space] "schedule a quick sync tomorrow at ten"
Result
Schedule a quick sync tomorrow at ten.

Local recognition. No audio leaves the device on this lane.

3 · Insert
Drop it into the app you were already using
Focused app

Text lands in the focused field — chat box, editor, terminal, ticket. No new window, no copy/paste dance.

Input
Focused window: Mail · Subject line empty
Result
Subject: Quick sync tomorrow at ten

Insertion verified on platforms listed in /compatibility.

4 · Translate
Translate where it is supported
Managed lane

Switch the session into the managed lane to translate between supported pairs. Optional, off by default, and limited to the pairs listed on /pricing.

Input
Spoken (EN): "Let's reschedule to Thursday morning."
Result
Inserted (DE): Verschieben wir auf Donnerstagvormittag.

Managed translation. See /pricing for supported language pairs.

5 · Command
Use supported voice commands
Per-app verification

Command mode is gated app by app. When an app is verified, you can run a named set of actions — never a blanket "control your computer" claim.

Input
Focused app: Code editor (verified)
Result
"Run tests" → executes the verified Run Tests command.

Command coverage per app is tracked in /compatibility.

What can block a workflow

Honest about where the loop breaks

We surface blockers up front so you can decide before installing — not after.

Gated
Wayland command surface not exposed

Some desktop sessions do not expose the APIs command mode needs. Dictation and insertion still work; command mode is reported as gated until verified.

Unsupported
Translation pair not in the supported list

If a language pair is not on /pricing, translation is unavailable for that session. Local dictation in the source language keeps working.

Limited
Microphone or input method blocked by the OS

Permission prompts and input-method conflicts are the most common block. /compatibility lists the fix per OS.

Next

Run the real check on your machine

Compatibility takes about a minute, no install needed, no account required.

Compatibility-first
See exactly what works on your OS, session, input method and audio stack.