A break from typing
Some messages are easier to say than to type. Myna aims to bring that convenience to Ubuntu: press a shortcut, speak, and your words appear in the app you are using. Canonical announced the technology preview on October 12, 2026..
After the recognition model has been downloaded, transcription works without an internet connection. Canonical says audio is neither uploaded nor stored. That makes the approach worth watching for people who prefer not to send dictation to a remote service.
Check your setup first
The preview supports Ubuntu 24.04 LTS, 26.04 LTS and 26.10 on amd64 or amd64v3 computers running GNOME on Wayland. These are hardware and desktop requirements, not country restrictions; the announcement does not describe a region-exclusive release.
Language support, accuracy and hardware needs vary with the selected engine. Try your own accent and microphone before relying on it for an important document. The announcement does not promise identical Spanish-language results on every machine.
Useful, but still unfinished
The project remains under active development, and its repository warns of substantial changes before a stable release. Its job is dictation, not controlling your computer through spoken commands.
Our suggestion is to start with a short test paragraph, check names and punctuation, and always read the result before sending it. Fewer keystrokes are welcome; accidentally sending words you never meant to say is not.
Sources and context
Sources used for this article. Follow the links to read the original material.
See the linked sources for more information. Corrections and contact →
