Canonical reveal Myna, a speech to text system for Ubuntu Linux

As part of their accessibility drive, Canonical have revealed Myna, their new in-development speech to text AI system for Ubuntu Linux.

In a post written by Jean Baptiste Lallement of the Canonical Desktop Team, they mention how "Speech recognition has become a common feature on modern platforms, and we think it should be a first-class experience on Ubuntu Desktop as well" with a privacy-first design.

For the upcoming Ubuntu 26.10 their current aim is just to get reliable desktop dictation. So you press a key, speak and the text will appear on-screen. How? They said it currently "uses speech recognition models running locally on your machine" with the initial release targeting Ubuntu Desktop on Wayland with GNOME. Other desktop environment support is to come sometime later. More advanced features like voice assistants, voice commands, desktop control, translation and automatic language detection are to come later too once this basic first step is ready.

As for the privacy side of it they outlined these points:

• While it is not restricted to local models, the initial implementation prioritizes speech recognition running locally on your machine.
• No internet connection is required once the necessary models are installed.
• The microphone is only accessed when you explicitly activate dictation.
• Audio is processed in memory and discarded after use.
• No audio recordings are uploaded to external services.

So far it seems they've only released the specifications and architecture documents as open source on GitHub.

Accessibility features like this are one area where AI and LLMs could actually be properly useful.

See more on the Ubuntu Discourse forum post.