The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Some links on this page are affiliate links: if you buy through them we may earn a commission, at no extra cost to you.
Ubuntu voice dictation currently means Myna, an optional speech-to-text technology preview rather than a feature included in a fresh Ubuntu installation. You activate it with a shortcut, speak into a focused text field, and Myna inserts the recognized words into the active application. Recognition runs on your computer through a selected model, so—after the model is downloaded—transcription can work without an internet connection.
Myna is still under active development. Its language coverage, accuracy, hardware needs, and desktop compatibility depend on the engine and model you choose. This guide explains the complete flow, installation, privacy boundary, supported environments, and the practical questions to check before relying on it.
As an Amazon Associate I earn from qualifying purchases.
What is Ubuntu voice dictation, and is Myna installed by default?
Ubuntu’s current desktop dictation project is Myna. It converts microphone speech into text and types that text into the application containing your cursor. It is deliberately a dictation tool, not a general voice assistant: it does not interpret spoken commands to control the desktop.
A fresh Ubuntu 26.10 Desktop installation does not include built-in AI tooling, and Myna is not preinstalled. Canonical describes Myna as a technology preview that is still changing. You add it yourself from Canonical’s PPA, install the configuration package, and complete setup in Myna’s settings. The same preview announcement lists Ubuntu 24.04 LTS, Ubuntu 26.04 LTS, and Ubuntu 26.10 as supported releases in its primary configuration.
Popular on Amazon
- 【90 Degree Full Function USB C Adapter】Supports the latest USB4 standard for up to 40Gbps of bandwidth, 8K video support, and up to 240W Fast charging; Support USB PD 3.1 Extended Power Range (EPR) including 140W, 180W and 240W. Your productivity is easily doubled. *Warm Tip: For the best fit, please make sure the USB-C port is fully exposed; thick or bulky cases may affect compatibility.
- 【Reliable Quality】Made from high-quality, scratch-resistant aluminum alloy, delicate metal frame. get excellent wear resistance and heat dissipation. Non-Slip Design for easier insertion and removal.
- 【Small and portable】Ultra thin size, ultra compact design, a petite physique that matches the minimalist design of your modern laptops. Coming with a slim figure that won't block the port next to the one it's plugged into.
- 【Compatibility】Widely work with most usb c, thunderbolt 4/3 devices. Compatibilit for ROG Ally, Steam Deck, Switch, MacBook Pro, Quest 3 VR headset, Surface Book 2, iPhone 18/17/16/15, Samsung Galaxy S23/S22/S21, Note 20/10, Google Pixel, ChromeBook, etc.
- 【Excellence Customer Support】If you experience any issues or cable failure, simply reach out to our dedicated customer service team. We provide a prompt response within 18 hours, providing you with the necessary technical support to resolve any concerns.
Because this is preview software, menu names, model availability, and supported desktop combinations can change. Treat the project as useful for evaluation and everyday experimentation, not as a frozen component with a long-term compatibility guarantee.
How does Myna turn speech into text?
The basic interaction is short: focus a text field, invoke Myna’s shortcut, speak, and stop dictation when finished. Myna provides visual feedback while it is listening or processing, then inserts recognized text into the focused application.
Recommended Free Tools
- Choose a destination. Click in a text box, document, terminal prompt, or other field that accepts keyboard input. The destination matters because Myna types through the desktop input system rather than writing a separate transcript file.
- Press the configured shortcut. Myna only accesses the microphone when you explicitly activate dictation. The exact key combination is the one you set in Myna’s configuration.
- Speak naturally. Audio is sent to the recognition engine running on your machine. The preview supports engine families including Parakeet, Whisper, and FunASR; each has different trade-offs in language coverage, recognition quality, and hardware demand.
- Watch the status feedback. The interface indicates that dictation is active. If you do not see that state, Myna has not started capturing audio, so check the shortcut and microphone selection before troubleshooting the target application.
- End dictation. Use the configured stop action or shortcut. The recognized result is inserted into the field that still has focus. If focus moved to another window, the text may be delivered there instead.
This is speech-to-text input, not a cloud conversation. Myna does not decide what action a spoken sentence should trigger; it produces text for another program to handle.
How do I install Myna on Ubuntu?
You need a listed Ubuntu release, a compatible desktop session, working microphone input, and internet access for the initial package and model downloads. Myna is installed manually; it is not part of the default Desktop image.
- Add Canonical’s Myna PPA. In Terminal, run:
sudo add-apt-repository ppa:canonical-desktop-team/myna - Refresh package metadata.
sudo apt update - Install the configuration package.
sudo apt install myna-config - Open Myna settings. Launch the Myna settings application from the app menu and follow its setup flow. Select a recognition engine/model, choose the microphone, and assign a shortcut.
- Download the required model while online. The first setup may require a substantial model download. Keep the computer connected until the selected model is installed and the settings page reports that it is ready.
- Run a focused-field check. Open a simple text editor, place the cursor in a blank document, press the shortcut, speak a short sentence, and stop. This separates Myna configuration problems from compatibility issues in a particular application.
Canonical’s preview instructions identify myna-config as the package to install. If the package cannot be found, confirm that the PPA was added for the correct Ubuntu release and that APT completed its metadata refresh; do not assume that a fresh installation already contains Myna.
Which desktop and hardware configurations are supported?
The October 2026 preview announcement lists Ubuntu 24.04 LTS, 26.04 LTS, and 26.10 on amd64 and amd64v3 systems using GNOME on Wayland. It also identifies GPU acceleration for supported NVIDIA GPUs, with support for other accelerators planned. The project’s live repository README contains broader, qualified notes, so compatibility depends on both your Ubuntu flavor and session.
Also popular on Amazon
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
- Ubuntu GNOME on Wayland: the principal configuration described for Ubuntu 24.04 and later.
- Xubuntu: the README describes Xfce on X11 for 24.04.
- Kubuntu: the README describes KDE Plasma 6 on Wayland from 26.04, while warning that some Plasma configurations are unsupported or best-effort.
Myna types through IBus. That implementation detail explains why text insertion can vary between applications and desktop configurations even when speech recognition itself works. A failure in one program does not necessarily mean the microphone or model is broken.
Engine choice also affects hardware requirements. The official material names the supported engine families but does not publish a single CPU, RAM, GPU, or model-by-model requirement table. Select a model appropriate to your machine and watch its own setup information rather than treating every engine as equivalent.
Is Ubuntu dictation processed locally, and what happens to the audio?
According to Canonical’s security explanation, Myna performs recognition locally through an inference snap. Once the required model has been downloaded, no internet connection is required for transcription. Canonical states: “Audio is processed in memory, discarded after use, and is not uploaded to an external transcription service.”
The preview announcement expresses the same boundary: “Once a model has been downloaded, no internet connection is required for transcription, and your audio is not uploaded or stored.” That means the speech-recognition step is local and does not depend on sending recordings to a remote transcription provider.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Local recognition does not mean that every piece of data involved in your workflow stays local. Myna inserts recognized characters into another application. That application may save the document, synchronize it, transmit it, or retain metadata according to its own design and account settings. For example, dictating into a web service still gives that service the resulting text once it is entered there; Myna’s audio-disposal statement does not override the receiving application’s storage or network behavior.
The privacy model therefore has two separate parts:
Also popular on Amazon
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
- Speech processing: Myna captures audio only after explicit activation, runs recognition locally, processes audio in memory, and discards it after use according to Canonical’s published description.
- Text handling: the destination application controls what happens to the recognized text after insertion.
If your requirement is that neither audio nor text leave the computer, use Myna with a local destination and review that application’s own synchronization and network settings.
Which languages and accents does Myna support?
There is no single Ubuntu-wide language list that applies to every Myna installation. Language support comes from the selected recognition engine and model, and Canonical says those engines trade off language coverage, accuracy, and hardware requirements. The project introduction also warns that model performance can vary substantially by language.
Free tools Windows power users keep installed
One-click scans. No signup required.
Canonical’s public preview materials do not provide a definitive, current language-by-engine matrix or comparative accuracy results. Do not infer that naming Parakeet, Whisper, or FunASR guarantees support for a particular language, dialect, or accent. Instead, evaluate the exact model offered in Myna settings against the language you need.
A sensible selection process is:
- Start with the language requirement. Confirm that the model description or its documentation explicitly includes your language. If no clear listing is available, regard support as unconfirmed.
- Consider your accent and vocabulary. General-language support does not guarantee good recognition of regional pronunciation, specialist terminology, names, or code.
- Balance quality with hardware. A model that offers broader coverage may require more memory or processing time. A lighter model may respond more easily on modest hardware but offer different language trade-offs.
- Try representative sentences. Use a short, non-sensitive sample containing the names and terms you actually dictate. Compare results without treating the exercise as a formal benchmark; Canonical has not published a universal accuracy ranking.
Canonical is asking users to provide feedback in their native languages and natural accents. That invitation is evidence that coverage is still being refined, not a promise that every language has equal support today.
Does Myna translate speech or control Ubuntu by voice?
No. Myna’s initial scope is transcription: it listens while explicitly activated and inserts words into the focused field. The project introduction places translation and automatic language detection outside that initial scope, and the preview announcement says Myna is not a voice assistant.
You can dictate text that another application later translates or acts on, but that second step belongs to the other application. Myna itself does not launch programs, change settings, navigate menus, or execute spoken commands as a desktop-control layer.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchPC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Also popular on Amazon
- Portable and powerful USB-C HUB: BENFEI USB Type-C HUB, with super-soft and knot-free silicone woven design cable, meets most mobile office needs. Compact, lightweight, stylish, and powerful portable USB C Hub equipped with 1 x HDMI port, 1 x 100W charging, and 3 x USB ports. 18-month warranty, 24-hour response, to ensure you feel at ease when using our product.
- Design centered on comfort and reliability: Thanks to BENFEI's end-to-end in-house cable production capability, in-house PCBA and assembly capability, using the industry's most advanced silicone woven design and process, 20cm cable in length, no knots, super-soft, the HUB is easy to use in all scenarios: laptop, tablet, stand etc. Super-soft, 25000+ life cycles, to meet your daily carrying and office needs.
- 100W Charging: Support up to 90W USB C pass-through charging via Type-C port to keep your laptop powered. 10W is reserved for other interface operations. No data and video function on the Type-C port.
- 4K HDMI Display: The HDMI port supports media display at resolutions up to 4K 30Hz, keeping every incredible moment detailed and ultra vivid. Please note that the C port of the Host device needs to support video output.
- Transfer Files in Seconds: Transfer files and from your laptop at speeds up to 10 Gbps with USB A 3.2 port. Extra 2 USB A 2.0 ports are perfectly for your keyboards and mouse.
What should I check when dictation does not work?
Most failures can be narrowed down by checking the activation state, audio input, model readiness, focus, and desktop-session compatibility in that order.
- No visual feedback appears: verify that Myna is running, that a shortcut is assigned, and that another program has not claimed the same key combination. Try assigning a temporary shortcut that is not used by your desktop.
- Myna activates but hears nothing: check the selected input device in system sound settings and confirm that the microphone has a visible input level. If the built-in microphone is unavailable or poor, an external USB microphone is optional, not required; Canonical invites testing with different microphones but does not require a particular model.
- The model is unavailable: reconnect to the internet and confirm that the initial model download completed. Offline transcription begins only after the required model is installed.
- Speech is recognized but no text appears: test in a basic text editor with the cursor visibly active. Because Myna types through IBus, an application or desktop configuration may not accept the generated input correctly.
- Behavior differs on KDE or another flavor: compare your session with the project README’s qualified notes. Some Plasma configurations are unsupported or best-effort, and the preview announcement’s primary support list should not be read as a guarantee for every desktop environment.
- Recognition is poor: review the selected engine/model, microphone placement, accent and vocabulary fit, and hardware load. The official sources provide no universal accuracy percentage to use as a pass/fail threshold.
When reporting a problem to the project, include the Ubuntu release, desktop and display-server session, selected engine/model, input device, and whether the problem is activation, recognition, or text insertion. That information maps to the separate layers in Myna’s workflow.
What are Myna’s current limitations?
The largest limitation is maturity. Canonical describes Myna as a technology preview under active development, and the repository warns that major changes may occur before a stable release. Installation and compatibility guidance should therefore be checked against the current project documentation whenever you upgrade Ubuntu or switch desktops.
Other practical limits follow directly from the design:
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
- It is not included in a new Ubuntu Desktop installation.
- It requires a model download before offline transcription is possible.
- Language and accent performance vary by model; no definitive universal matrix is published in the reviewed sources.
- Recognition quality and responsiveness depend on the selected engine and your hardware.
- Text insertion relies on IBus and can be affected by the destination application or desktop configuration.
- Translation, automatic language detection, and spoken desktop control are outside the initial scope.
These constraints do not make Myna unusable; they define where it fits. It is best understood as local desktop dictation that you can configure and evaluate, not as a finished, all-purpose voice interface.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.How should you evaluate Myna before relying on it?
Start with the exact workflow you care about rather than choosing an engine by name alone. Confirm that your Ubuntu release and desktop session are within the documented compatibility notes, install the model while online, and test the applications where you will actually dictate.
Also popular on Amazon
- 【Read before You Buy】 Note: This adapter is USB 2.0 version and cannot transmit HDM, VGA, or other video signals. Nevertheless, they are fully capable of charging devices,duplicating files, and can be seamlessly integrated with USB-C earphones, wireless network adapters, and SD card adapters.
- 【Easy to Use and Safe】Thanks to modern manufacturing techniques, we've made these adapters sufficiently compact so that they can remain inserted in your device without noticeable protrusion or inconvenience. This means you don't have to constantly plug and unplug them, reducing the likelihood of wear and misalignment, and making them more convenient to carry around.
- 【Reliable Quality】Engineered for enhanced durability, durable aluminum alloy shell material,get excellent wear resistance and heat dissipation,the male USB C and female USB connectors & the male USB and female USB C connectors are designed to be plugged and unplugged up to 20000 times. Provides data transfer, device charging, memory space expansion, and additional computer peripherals.
- 【Think more for you】Do you need to connect a USB-C-enabled device to an odd device that only has USB-A ports? Then these USB-A male to USB-C female adapters are made for you.Simply insert the adapter into the USB-A port on the device, and you can instantly connect your USB-C device to the device that originally didn't have the correct connection port.
- 【Trusted xiwxi Quality and Service】As a responsible brand seller, you will receive xiwxi's 12-month Quality assurance and lifetime friendly customer service, you're not just buying a product,you're investing in peace of mind with all-round quality and exceptional customer service.
Use representative, non-confidential sentences in each language or accent you need. Check whether specialist words are recognized, whether text lands in the right field, and whether the machine remains responsive during transcription. Then review the privacy boundary: Myna’s audio handling is local, but the application receiving the text may synchronize or transmit it.
If the results are acceptable, keep a fallback keyboard workflow because preview software can change. If results are inconsistent, try another available model, a different microphone, or a simpler destination application before concluding that Ubuntu’s speech recognition cannot meet your needs.
Where can I follow changes to Ubuntu dictation?
Canonical’s Myna technology-preview announcement explains the current setup and supported preview configuration. The canonical/myna repository contains evolving desktop notes and limitations. For the project’s goals and scope, see Canonical Desktop’s Myna introduction. Canonical’s Ubuntu 26.10 security article documents the local-processing and audio-disposal claims, while the Ubuntu AI wiki clarifies that fresh Ubuntu Desktop installations do not include built-in AI tooling.
Frequently Asked Questions
Can Myna be used without an internet connection every time?
Yes, after the selected recognition model has been downloaded and installed. Internet access is still needed for the initial package and model setup, and may be needed later if you change models or update the software.
Will Myna work in every Linux application that accepts text?
Not necessarily. Myna injects text through IBus, so application toolkits and desktop configurations can affect insertion. A simple text editor is a useful control case when an individual program does not receive dictated text.
Is an external microphone required for Ubuntu voice dictation?
No. A built-in microphone can be used if it provides a usable signal. An external USB microphone is an optional way to address missing or poor input, and Canonical does not require or endorse a particular model.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsCan I dictate in two languages automatically in one session?
Do not assume that behavior. Automatic language detection is outside Myna’s initial scope, and the available language behavior depends on the selected recognition model. Choose and test a model for the language you intend to use.
Does local transcription guarantee that dictated documents stay private?
No. Myna’s published privacy statements concern audio processing and transcription. Once text is inserted, the destination application’s saving, synchronization, account, and network policies determine where that text may go.

