ON-DEVICE DICTATIONVERSION 0.1.0

macOS preview available

Capstan

Speak here. Type anywhere.

Hold a key, speak, and release. Capstan turns your voice into cleaned-up text and places it wherever your cursor already is.

The shortest path from thought to text.

01

Push to talk

A physical keypress makes the recording boundary explicit. Capstan listens only when you ask it to.

02

On your device

Speech recognition can run locally with Apple SpeechAnalyzer or Parakeet, without sending every utterance to a server.

03

Types anywhere

The result lands at the current cursor, so your documents, messages and tools remain where the work lives.

04

Cleans as it goes

Formatting and personal dictionary corrections turn raw recognition into text that is ready to use.

05

Focused by design

No new editor, inbox or account-shaped workspace. Capstan is an input instrument, not another destination.

06

Built for recovery

Recent dictation can be replayed or repaired without retaining a permanent archive of your microphone audio.

Three movements. One finished sentence.

  1. 01

    Place the cursor

    Choose any editable field in the application you already use.

  2. 02

    Hold and speak

    Keep the push-to-talk key down for exactly as long as the utterance lasts.

  3. 03

    Release to type

    Capstan transcribes, cleans up and inserts the finished text at the cursor.

Bring Capstan onto your device.

The macOS app is used in daily work. This preview disk image is signed with a Developer ID, notarized by Apple and stapled for offline verification.

RELEASE0.1.0 CHANNELPREVIEW STATUSNOTARIZED

PLATFORM 2

Windows

Real-hardware validation pending

MACOS RELEASED 30 August 2026 · 9.8 MB · SHA-256499c6637cafeda863908e67f7db26ff7f05a06e7075861eed82405cfb55e77f0

Windows is implemented and exercised in CI, but nobody has yet held the key and spoken into a real Windows microphone. It will not be presented as a working download until that pass is complete.