Uvoxus Voice Assistant is a smart and flexible voice assistant for Windows, created to make interacting with your computer fast, convenient, and intuitive. Forget about routine mouse clicks—control your system, applications, media, and workflows with simple voice commands.
The assistant features a modern interface and deep customization capabilities: from creating simple commands to open folders, to writing complex scenarios that automate your daily tasks.
The project is constantly evolving, receiving regular updates to improve stability and add new features based on user feedback.
Uvoxus gives you a choice between two leading speech recognition technologies:
- Google Speech Recognition (Requires Internet): High accuracy for a wide range of everyday phrases.
- VOSK (Works Offline): Guarantees complete privacy and fast response times without the need for an internet connection.
You can also enable Hybrid Mode to leverage the strengths of both engines for maximum accuracy.
The program features a localized interface and extended support for speech recognition.
In a world where software is increasingly moving towards subscription models, Uvoxus follows a different path. This assistant is the result of enthusiasm and a desire to create a truly convenient tool accessible to everyone.
- ✅ No Subscriptions: No monthly fees or hidden costs.
- ✅ All Features Available Immediately: No "Pro" or "Premium" versions.
- ✅ No Ads: Nothing distracts you from your work.
- ✅ Free Updates: Always.
My goal is to give you a powerful tool, not to sell another product.
These are the two key ways to automate with Uvoxus.
A Command is a single simple action tied to a voice trigger. Ideal for quick, atomic tasks.
- “Open browser” → Opens the web browser.
- “Press Enter” → Presses the Enter key.
- “Launch Photoshop” → Launches
photoshop.exe.
A Scenario is a powerful sequence of multiple actions triggered by a single phrase. Scenarios allow you to automate entire workflows.
- You can change the order of actions by dragging them in the editor.
- You can add pauses between actions.
Example Scenario "Work Mode":
- Set power plan to "High Performance".
- Open VS Code.
- Pause for 2 seconds.
- Open GitHub website.
- Set volume to 50%.
- 🌐 Browser Control: Open websites, new tabs, switch between them, refresh, and scroll pages.
- ⌨️ Keyboard Emulation: Configure key presses and complex combinations (
Ctrl + Shift + Esc), as well as dictate text via voice. - 💻 Console Commands: Execute any system commands, including in hidden mode without opening the console window.
- 📂 Quick Access: Instantly open system folders: "Downloads", "Documents", "Pictures", and others.
- 🗑️ Empty Recycle Bin: Clean up your system with one command.
- 🖼️ Screenshots: Take screen captures with your voice.
- 💡 Dynamic Hints: The assistant offers random commands on the main screen to help you explore its capabilities.
- 🎛️ Power Management: Change Windows power plans ("Power Saver", "Balanced", "High Performance").
- 🔆 Brightness Control: Set the desired screen brightness level (for supported devices).
Make the assistant unique by adding your own response sounds! You can assign a unique audio file or a set of sounds to any command or scenario.
- 🎵 Assign sounds to both built-in and custom commands.
- 🎤 Use your own files: Supports
MP3,WAV,OGGformats. - 🎲 Random Responses: Set multiple sounds for one action, and the assistant will choose one at random.
- 📁 Audio Packs: Organize sounds into folders within the
audiodirectory for easy navigation in the menu.
- Find the
audiofolder next to the program's.exefile. - Copy your sound files there (you can create subfolders for organization).
- In the command or scenario editor, click the "Select" button.
- Save the changes. Now the assistant responds with your voice!
💡 Tip: Record short phrases like "Done!", "On it!", "As you wish!" and assign them to frequently used commands to make interaction more lively.
| System | Support | Notes |
|---|---|---|
| Linux | ❌ | Not supported |
| macOS | ❌ | Not planned |
| Windows 7 / 8 | ❌ | Not planned |
| Windows 10 | ✔️ | Fully Supported |
| Windows 11 | ✔️ | Recommended |
| 📂 Resource | 🌐 Link |
|---|---|
| Latest Version | Download from GitHub Releases |
| All Releases | Version History |
This is a false positive. Uvoxus is complex software that interacts deeply with the OS: it emulates key presses, manages windows, and launches/closes processes. Such behavior can appear suspicious to antivirus software, especially since the free project does not have an expensive digital signature.
If you downloaded the program from the official GitHub page, it is absolutely safe. Simply add the assistant folder to your antivirus exclusions.
This is necessary for the assistant to have sufficient rights to manage other programs (e.g., those running as administrator) and to correctly execute all system actions without errors.
- Download and Unzip: Download the archive with the latest version. Create a separate folder for the program (e.g.,
C:\Uvoxusor on the desktop) and extract the contents there. - Launch the Assistant: Double-click
Uvoxus.exe. - Open Settings: Go to the "Settings" tab.
- Select Microphone & Sensitivity: In the "Audio & Sensitivity" section, find "Active Microphone" and select your main device. This is the most important step! Also, adjust the sensitivity to your liking.
- Set Name: In the settings on the main page, find the name input field and enter one or more names for activation (e.g.,
Jarvis,Assistant). - Save Changes.
- Test: Return to the "Home" tab and speak the assistant's name. The status should change to "LISTENING...", and the animated indicator will start reacting to your voice.
✨ Done! Now you can control your PC with your voice. Try saying: “Open calculator” or “What is the volume now”.
💡 Tip: For best speech recognition, use the "Microphone Setup Wizard" in the settings. It will visually help you find the ideal sensitivity for your voice and background noise level.
If you like the assistant, the best thanks is to help it become better known. 🌟 Give a ⭐ Star on GitHub!











