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.
Type with your voice
Speak. Skald wires it back.
A dictation tool for macOS, Windows and Linux. Tap one key, speak, release — Skald wires clean text back to where your cursor is. Mail, Slack, your IDE, the address bar. Audio never leaves memory.
The two modes plus one
One key. Three jobs.
All three live on the same hotkey. Skald decides which job to do from whether you have a selection and how long you hold.
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.
What Skald actually does
A tool. Not magic.
Four things, done right — for every field on your machine.
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).
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.
Your dictionary
Names, jargon, product codes, the way your team spells things. Add them once in the menu-bar — Skald never writes them back wrong. Personal to your machine.
Audio stays home
Audio lives in memory, then is gone. No disk cache, no backup, no "anonymous" telemetry. No tracking, no analytics — your voice is yours.
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.
-
Website analytics
This website is measured. Cookieless, EU-hosted, no cross-site tracking. We see which texts get read — not who you are or where else you've been.
Pricing
Fair pricing — pay for what you use.
Three plans. Clear limits. No hidden tiers, no sales calls.
Free
For trying it out.
$0 / month
- 50 dictations per month
- Dictate, Command and Brain-Dump
- Personal dictionary
- No card required
Pro
For daily use.
$9 / month
- Unlimited dictations with a fair daily budget
- Command mode on selections
- Full AI cleanup
- Personal dictionary
Team
For shared workbenches.
$12 / seat / month
- All Pro features, per seat
- Consolidated billing
- Role permissions (Owner / Admin / Member)
- Per-member device management