OpenDMG
Vocula icon

Vocula for Mac

Hold-to-talk dictation in up to 100 languages, fully on-device with no account.

By vitaly-kashtalyan. Free and open source, GPL-3.0 licence.

Get it with OpenDMG View source on GitHub

Vocula at a glance

Version
1.0.0
Released
10 September 2026
Download size
14 MB
Works on
Apple silicon and Intel
Licence
GPL-3.0
Category
Audio and Music
Developer
vitaly-kashtalyan
GitHub stars
6

About Vocula

Local dictation for macOS. Hold a key, speak, and the transcript is pasted at the caret. Recognition runs entirely on your Mac.

How to install Vocula on a Mac

  1. Get OpenDMG. It is a free app store for open source Mac apps. Download OpenDMG.
  2. Search for Vocula and press Get. OpenDMG downloads version 1.0.0 from vitaly-kashtalyan's own GitHub release.
  3. Open it. The download is checked against its SHA-256 fingerprint and its signature is checked on your Mac before it lands in Applications.

Updates to Vocula show up in OpenDMG and install with one button. No account is needed.

Prefer to do it by hand? The developer's file is on GitHub: Vocula.dmg (14 MB).

What is new in Vocula 1.0.0

## 1.0

Vocula has been doing this job every day for months. Nothing in this release
changes how it works — the version number is what changed.

A number starting with 0 reads as "preview", and this stopped being one a long
time ago. Hold a key, speak, and the words land at your cursor: that has been
true, and quietly reliable, for a while now. 1.0 says so out loud.

One fix ships with it.

---

## What's Changed
### Fixed
* fix: say when a dictation never reached history by @vitaly-kashtalyan in https://github.com/vitaly-kashtalyan/vocula/pull/19

**Full Changelog**: https://github.com/vitaly-kashtalyan/vocula/compare/v0.1.8...v1.0.0

---

**Dictation that never leaves your Mac.** Hold a key, speak, and the words land
where your cursor already was — in any application, in any of the 100 languages
Whisper knows.

No account, no subscription, no server, and nothing you say ever leaves your
Mac. That is checkable rather than promised: the app reaches the network in two
places, both of them this repository's own releases — it fetches the speech
model once, and asks once a day whether a newer version exists.

### Install

Open **Vocula.dmg** and drag Vocula into Applications **before launching it** —
macOS ties the permissions you grant to where the app lives. Then allow the
microphone and Accessibility, and let it download the 1.6 GB speech model once.
…

More Audio and Music apps

All Audio and Music apps