Dictate
Hold, speak, release.
Hold the key, speak, release. Skald reads the app, window and field and matches the register — short in Slack, complete in Mail, untouched in code.
Up to 5× faster than typing
Hold one key, speak, let go: finished text right where your cursor blinks. In Mail, Slack, your IDE. Speech runs at 200+ words a minute, typing at about 45. That hands you back up to 7 hours a week — do the math below.
No credit card. 50 dictations a month, free.
Three ways to speak
One key, three paths. Your selection and the length of the dictation choose the shape.
Dictate
Hold the key, speak, release. Skald reads the app, window and field and matches the register — short in Slack, complete in Mail, untouched in code.
Command
Select text, hold the key, say what it should become. Skald replaces the selection in place — in the form you named.
Brain-Dump
A separate window for long dictations. Skald sorts fragments, pulls out a TL;DR and turns the spoken material into headings and action items.
The time factor
Three sliders, honest math. No email, no signup — the numbers never leave your browser.
132
hours back every year
≈ 36 minutes on every workday
6,600 €
of working time recovered per year
at 50 € an hour
Skald Pro costs 108 € a year.
That is roughly 61× back on what you pay.
No credit card. Installed in two minutes.
What Skald actually does
Four things, done right — for every field on your machine.
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).
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.
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 lives in memory, then is gone. No disk cache, no backup, no "anonymous" telemetry from the app. Your voice is yours.
Your workbench
A few clear rules are enough. Skald learns your words, your snippets and the register you write in.
Teach Skald the terms it often gets wrong once. Private entries stay yours; the team pool is shared.
Say “@signature” and the full snippet appears in your text. Private and shared snippets use separate pools.
Set rules per category: Messaging, Email, Code, Document, Browser and Terminal. Add to the default or replace it.
Describe your role, voice and sign-offs once. That context flows into every dictation.
For power users: your own prompt instead of Skald's default, with full control over cleanup.
Manifesto
Three sentences about privacy soothe no one. Four architectural decisions do.
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.
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.
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.
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.
Pricing
Three plans. Clear limits. No hidden tiers, no sales calls.
For trying it out.
€0 / month
For daily use.
€9.00 / month
For shared workbenches.
€12.00 / seat / month
All prices are net, plus statutory VAT. The tax actually due depends on your country and any reverse-charge treatment, and is calculated authoritatively at checkout.