Canonical, the company behind Ubuntu, is making a new speech to text application. Ubuntu 26.10 is expected as the first release to include it.
The new app is named myna, a bird that’s known for its ability to mimic human speech.
Image by Wild Pixar from Pixabay
“Press a keyboard shortcut, speak naturally, and see the resulting text appear in the application you’re using.” This will be the initial myna experience!
The speech recognition models run on user’s local computer. No internet connection is required (once models are installed). The microphone is accessed only when user activates the recording process, and, audio is processed in memory and discarded after use, no uploading!
The myna project is in very early stage. The initial release will focus on Ubuntu with default GNOME desktop support, while, additional desktop environments support will be available in the future. And, not only local models, it will probably support cloud models runs on remote servers.
See this discourse page for more about the new Myna speech to text introduction.
Or see the project page, though at the moment of writing there’s no code there.
