AI-powered voice typing is coming to Ubuntu in Myna, a speech-to-text feature that lets you talk into any valid text field. It’s still a work in progress, but I grabbed an early build to see how it’s shaping up.
With Ubuntu 26.10 now entering its freeze, the user-facing pieces of myna are falling in to place. This week, a new GNOME Shell extension was added to default installs to provide an on-screen indicator when myna is listening and recording.
To be clear: Myna is not a GNOME Shell extension. It’s an orchestrator that manages loading the AI model, listening for hot-key activation, passing audio from your microphone to the model to be transcribed and feeding the output back to a text field over IBus1.
But the extension is important as it’s the bit you see, telling you when Myna is actively listening to and processing audio.
Below is a screen recording where I activate Myna, and use it to transcribe a sentence into the Text Editor app:
The GitHub for myna says2: “Whether you are looking to dictate text hands-free, improve accessibility, or streamline your workflow, myna brings seamless voice recognition directly to your Linux ecosystem.”
Myna is activated by pressing (but NOT holding) a hotkey to activate listening. In my testing this was configured to super + t.
An onscreen display (OSD) shows when listening is active. As you talk, an animated ‘wave’ inside the OSD oscillates, which is a nice bit of confirmatory feedback so you know it’s working.
When you’re done, you press the same keyboard shortcut again. The OSD animation goes flat as the audio is transcribed in the background. After a short pause, the text appears in the text field of whatever app was focused when you activated speech-to-text.
What happens if you close or minimise the ‘target’ window? The myna OSD lets you know focus was lost.
But mousing out of the window or alt-tabbing away shouldn’t, per the spec. Myna keeps track of the intended target – it won’t end up in any text field you highlight subsequently.
If it doesn’t hear any audio, it tells you so; it doesn’t transcribe silence!
Different AI models will power Myna
No audio leaves your device, say Canonical. Myna doesn’t rely on cloud models; it works entirely offline, figuratively and literally. And any audio that is used for transcription is not stored, logged or trained on.
In my testing myna used Whisper. But a variety of local AI models will be available (all as snaps), including some that can run solely on NVIDIA GPUs, some CPU only, some that have broader language support, etc.
By the time this feature is ready for wider testing, the best local AI model for your system’s hardware is used.
I haven’t found any of the voice snaps, or the myna orchestrator, on the Snap store yet, but I got it things up and running from source code on GitHub. As the feature will be distributed as a snap
The good news is that it worked, fairly accurately, albeit a tad slowly (I was running WIP source code in a virtual machine, so I’m taking nothing as read). Input landed in most fields I tried, including the text editor, GNOME Shell overview and Firefox.
Dictation for Ubuntu, not dictated by Ubuntu
Canonical will take a deliberate approach to AI features in Ubuntu, per its VP of Engineering, Jon Seager. He said using AI for its own sake rarely works, and that any features found in Ubuntu will need to offer real value to users.
Not a fan of AI?3 Myna is expected to be opt-in and. Both it and the speech recognition models that are downloaded on-demand will be Snaps, so easily removable (and avoidable).
- A Wayland-native inout method is planned for a future release. ↩︎
- If you play AI writing-tell bingo, congrats on completing a row! Full house would’ve required “with ease”, “elevate” and an “it’s not X, it’s Y” construction. ↩︎
- The Myna repo has nested folders of cross-referencing
.mdfiles, structured and worded to unambiguously steer and assist AI agents in understanding/set out constraints. However, it’s not clear if any of Myna’s code itself has been generated by AI tools. ↩︎