Two modes on one key
Hold Fn → speak → release. Text lands at the cursor (Dictate). Hold Fn with text selected → tell Skald how to change it ("shorter", "as bullets", "in English") — and the selection is replaced (Command).
Available now
Speak into any app on macOS or Windows
Hold the hotkey, say it, let go. What lands in the field is finished text, shaped for the app you are in. Linux is in closed beta.
macOS
Download for MacWindows
Your PCThe first time you run the installer, Windows shows a SmartScreen warning. What to click →
- Free to start
- No credit card
- macOS 13+ · Windows 11
Four steps to a working setup
Open the installer and drag Skald to Applications (Mac), run the setup (Win), or launch the AppImage / install via AUR (Linux).
Skald runs as a menu-bar app on macOS, a tray app on Windows, and an AppIndicator on Linux.
Grant permissions on first launch.
Microphone, Accessibility, Input Monitoring (macOS) — microphone + tray permissions (Windows) — microphone + xdg-portal hotkey (Linux). Skald walks you through each pane.
Create your account in the browser tab Skald opens.
Skald sends you to heyskald.com once. Sign up or log in, confirm your email address, and the machine stays paired with your account from then on.
Hold Fn (Mac) or your chosen key (Win), speak, release.
Text appears where your cursor is. In any application.
Knows where you're typing
Skald sees the active app, the window, the browser address bar and the focused field. It figures out on its own whether you're writing a Slack DM, a customer email or a commit message, and shapes the text to match.
Lands in every field
Skald puts finished text at the cursor. Stage 1 sets the field value, Stage 2 types Unicode, Stage 3 borrows the clipboard for a moment — then restores it.
Audio stays home
Audio lives in memory, then is gone. No disk cache, no backup, no "anonymous" telemetry from the app. Your voice is yours.
Hold, speak, release.
Text appears at the cursor. Cleaned in tone for the app you're in — Slack reads casual, Mail reads polished, code stays untouched.
Reshape a selection.
Select text, hold the key, say what to change. "Shorter." "More formal." "As bullets." "In English." The selection is replaced — no diff to review.
Long form, own window.
When you have more to say than fits in a field. Opens a Skald window, captures everything, cleans it into structured prose you can drop where you want.
System requirements
- macOS 13 Ventura or newer (Apple Silicon or Intel)
- Windows 11 (x64 or ARM64)
- Linux with GTK4 (AppImage, AUR; Wayland preferred, X11 fallback)
- About 60 MB of disk space
- Microphone, Accessibility / Input-Monitoring permissions (and their Win/Linux equivalents)
Manifesto
Privacy isn't a promise, it's the architecture.
Three sentences about privacy soothe no one. Four architectural decisions do.
Audio lives in memory.
Skald never writes audio files to disk. Not as a cache, not as a debug artefact. What you say is heard once — and then it's gone.
Skald servers in the EU.
Audio leaves your machine only to be turned into text. Our own servers are in the EU. For speech recognition and AI cleanup we work with specialised partners — each one named in the privacy policy, each one with model training on your data turned off.
No model training on your voice.
Your voice is never used to train anyone's models. We pay the surcharge to keep your speech out of training data — that's on us, not on you.
In the product: no tracking, no telemetry.
No analytics pixel in the product. No crash reporter. No "anonymous" heartbeat from your Mac, Windows, or Linux app. Your audio stays in memory and is never written to disk.
- Made in Germany — built in Ahrensburg near Hamburg
- GDPR-compliant
- Servers in the EU
What it costs
- Free
- 50 dictations a month
- Trial
- 7 days of Pro, no card
- Pro
- €9.00 / month · net, monthly, cancel any time
Before you install
How does the trial work?
You get 7 days of the full Pro feature set. Skald shows the trial-day counter right in the app and emails you a reminder three days before it ends. If you don't actively switch to Pro, your account drops to the free plan — no hidden auto-charge.
Where is my audio? Where are my transcripts?
Audio is only in memory during a recording — never written to disk on your machine or on our servers. Transcripts pass through cleanup and are not logged by default. Our own servers are in the EU. For speech recognition and cleanup we use specialised AI partners with model-training opt-out; they are all named in the privacy policy.
Which platforms does Skald support?
macOS 13+ and Windows 11 (x64 and ARM64) are available to download today. Both clients ship the same feature set — Dictate, Command, Brain-Dump, the personal dictionary, settings. macOS is the oldest channel and the default route; Windows is now stable. The Linux client is built natively on GTK4 and is in closed beta; join the waitlist for early access.
What happens if I'm offline?
Skald needs an internet connection. Recognition and cleanup happen on our servers; without a connection the app pauses and tells you. An offline mode isn't part of the current product.
Does Skald work in every app?
In nearly every text field on your machine — Mail, Slack, Notion, your IDE, the address bar, terminal, search bars, web forms. If the cursor blinks somewhere, Skald can write there. Apps that block accessibility access (rare) are the only exception.
Can I cancel at any time?
Yes. Go to heyskald.com/billing → Manage subscription and cancel in one click. Cancellation takes effect at the end of the current billing period; Skald keeps working until then. No lock-in, no retention hotline.
Download and start
Already installed? The account is created from inside the app: Skald opens the right browser tab on first launch.