Ubuntu Desktop is getting Myna, a private speech-to-text dictation project, as a technology preview. A few months after Canonical first introduced it, Myna is installable and open to community testing. It is an optional Ubuntu 26.10 feature that gives real-time visual feedback during speech recognition. Named after the speech-mimicking myna bird, it works by letting you press a shortcut, speak, and have Myna transcribe your words directly into the application you are using.
The preview is aimed at people who rely on dictation every day and at those who use it only occasionally. Canonical is asking for feedback from both groups. Myna is still under active development, so you should expect some rough edges. The core experience is in place, though.
Local speech-to-text
Speech recognition runs entirely on your machine. After a model has been downloaded, no internet connection is required for transcription, and your audio is not uploaded or stored.
Myna supports several speech recognition engines: Parakeet, Whisper, and FunASR. Each has different trade-offs in language support, accuracy, and hardware requirements. If you have a supported NVIDIA GPU, Myna can also offer a GPU-accelerated engine, and support for additional accelerators is planned.
Trying the preview
Myna is available on Ubuntu 24.04 LTS, Ubuntu 26.04 LTS, and Ubuntu 26.10, on amd64 and amd64v3, using GNOME on Wayland. To install the preview, add the PPA and then install the configuration package:
sudo add-apt-repository ppa:canonical-desktop-team/myna
sudo apt install myna-config
Next, open Myna settings from Activities and follow the setup. Once setup is complete, place the cursor in a text field, press the configured hotkey, and start talking.
What Canonical wants you to test
Try Myna with the applications you normally use, in your native language or in any language, with your natural accent. Canonical is particularly interested in feedback on:
- Transcription quality
- Responsiveness
- Language and accent support
- Application compatibility
- Setup and onboarding
- Anything that feels awkward or unexpected
Feedback from different machines and microphones is also useful. The team wants to understand how well the current models and defaults behave across a broad range of Ubuntu systems.
Myna is deliberately focused on dictation for now. It is not a voice assistant and does not control the desktop through voice commands.
Key Features at a Glance
- Local processing: Speech recognition runs entirely on your machine, with no internet connection needed once a model is downloaded. Your audio is not uploaded or stored, which keeps dictation private.
- Multiple engines: Parakeet, Whisper, and FunASR are supported. Each trades off language support, accuracy, and hardware requirements, so you can pick the one that suits your needs.
- Hotkey dictation: Press the configured hotkey and speak, and Myna transcribes directly into the focused application.
- Visual feedback: Real-time visual feedback shows the state of speech recognition as you talk.
- GPU-accelerated engine: Supported NVIDIA GPUs can run a GPU-accelerated engine. Support for additional accelerators is planned.
- Broad platform support: Ubuntu 24.04 LTS, 26.04 LTS, and 26.10 are supported on amd64 and amd64v3, using GNOME on Wayland.
- Dictation focus: Myna is not a voice assistant and does not control the desktop through voice commands.
Availability
Myna is a technology preview. You can install it on the supported Ubuntu releases listed above with the PPA and myna-config package commands shown earlier. The project is developed in the open at github.com/canonical/myna, where you can follow development and report feedback.
