distronews.com stable7.3.1
Ubuntu Blog

Myna speech-to-text is now available as a technology preview

ubuntu.com

Key points

Canonical has released Myna, its local speech-to-text dictation tool for Ubuntu Desktop, as a technology preview and is asking the community to test it. Myna is an optional feature of Ubuntu 26.10 and is still under active development, so rough edges are expected.

What it does

  • Pressing a shortcut starts dictation, and the spoken text is transcribed straight into the application in use, with real-time visual feedback.
  • Recognition runs entirely on the local machine; audio is neither uploaded nor stored.
  • After a model has been downloaded, transcription works without an internet connection.
  • Several recognition engines are supported, including Parakeet, Whisper and FunASR, which differ in language support, accuracy and hardware requirements.
  • With a supported NVIDIA GPU, a GPU-accelerated engine can be offered; support for other accelerators is planned.
  • Myna is limited to dictation for now: it is not a voice assistant and does not control the desktop by voice commands.

Who can try it

  • Available on Ubuntu 24.04 LTS, Ubuntu 26.04 LTS and Ubuntu 26.10.
  • Architectures: amd64 and amd64v3.
  • Requires GNOME on Wayland.

How to install

  • Add the PPA and install the myna-config package:
sudo add-apt-repository ppa:canonical-desktop-team/myna
sudo apt install myna-config
  • Open Myna settings from Activities and go through the setup.
  • Then place the cursor in a text field, press the configured hotkey and speak.

Feedback wanted

  • Testers are asked to use Myna in their usual applications, in their own language and natural accent.
  • Areas of particular interest: transcription quality, responsiveness, language and accent support, application compatibility, setup and onboarding, and anything awkward or unexpected.
  • Reports from a variety of machines and microphones are wanted, to judge how the current models and defaults behave across Ubuntu systems.
  • People who rely on speech-to-text are especially asked to describe their experience and what is still missing.

Get involved

  • Development happens in the open at github.com/canonical/myna.
  • Bugs can be reported on GitHub, where there are also discussions to start or join.
  • Contributions of code, documentation and ideas are accepted.

Summary by DistroNews, based on the original post.

A few months ago, we introduced Myna, our project to bring private, local speech-to-text dictation to Ubuntu Desktop. Named after the speech-mimicking myna bird, Myna is an optional Ubuntu 26.10 feature that offers real-time visual feedback during speech recognition. Since then, Myna has grown into something you can install and use on your desktop. Today, […]

This is the summary Ubuntu Blog published with the story. The full text is on the original page.

Read the original at ubuntu.com