Install and configure DysVoxa Free
Everything you need to get DysVoxa Free running — from download to daily use. Covers system requirements, installation, microphone and output setup, voice profiles, and troubleshooting.
System requirements
All speech recognition and correction run locally on your computer, so hardware matters. Below the minimum specs the app may still work, but with higher latency.
Windows 10+ (64-bit)
Windows 10 or later, 64-bit required.
16 GB RAM
Minimum for real-time speech recognition and correction.
4 cores / 8 threads
Multi-core CPU for real-time processing. No GPU required.
3 GB disk space
Models and application combined.
Any microphone
USB or built-in.
Installation
DysVoxa Free ships as a Windows installer (approximately 1.3 GB including speech models). The installer is signed with a self-signed certificate from DysVoxa LLC.
1. Run the installer
Double-click the downloaded setup file. If Windows SmartScreen appears, click More info → Run anyway. The publisher shows as DysVoxa LLC.
2. Accept the license
Review the MIT license text, select I accept the agreement, and click Next.
3. Choose install location
Default is C:\Program Files\DysVoxa Free. Change if needed, then click Next.
4. Install and finish
Click Install. Approximately 1.3 GB of model files are copied. A desktop shortcut and Start Menu entry are created automatically.
Windows SmartScreen warning: Because the installer uses a self-signed certificate (not a commercial CA), Windows shows a blue “protected your PC” screen. Click More info → Run anyway. This is expected for an open-source beta.
First launch — setup wizard
On first launch, DysVoxa opens the Setup tab with two guided steps: Devices and Voice Profile.
Step 1 — Devices
- Microphone: select your microphone from the list. If none appears, the system default is used.
- Output routing: choose where corrected speech plays — speakers, virtual microphone, or both.
- Virtual microphone install: if you select Virtual Microphone and the driver is not installed, click Install virtual microphone and approve the UAC prompt. VB-CABLE is installed automatically.
- Click Next to proceed to the Voice Profile step.
Output routing options
Speakers
Play corrected speech through your speakers or headphones. Best for face-to-face conversation.
Virtual microphone
Send corrected speech to a virtual mic that Zoom, Teams, Discord, and other apps select as input. Requires VB-CABLE driver.
Speakers + virtual mic
Output to both simultaneously — hear it yourself while others hear it in calls.
Step 2 — Voice profile
- Use a profile: select an existing profile from the list and click Next.
- Create a new profile: enter a name, select your dysarthria type and severity, then read short calibration phrases so DysVoxa learns your speech patterns.
- Skip for now: try the app without a profile. You can create one later from the Setup tab.
After completing or skipping the Voice Profile step, click Next to finish setup. The app is ready — switch to the Talk tab.
Using the Talk screen
The Talk tab is where you use speech recognition and correction day to day.
1. Start speaking
Click Start speaking. The button turns red and a 25-second countdown begins.
2. Speak naturally
The Raw recognition panel shows what the speech engine hears in real time.
3. Review correction
The Corrected panel shows the processed text. If correction is enabled, it appears automatically.
4. Speak the output
Click Speak to have DysVoxa read the corrected text through your selected output.
Toggle dark mode with the sun/moon icon in the top-right corner. When the virtual microphone is selected, other applications (Zoom, Teams, Discord) can select “CABLE Output” as their microphone input to hear DysVoxa’s corrected speech.
Settings — speech mode, output, and correction
The right sidebar on the Setup tab contains three settings cards. Adjust these to tune recognition speed, output routing, and correction quality.
Speech mode
Standard
Fast transcription. Not retrained for dysarthric speech. Recommended for most users and most speech patterns.
Advanced
Slower but more accurate. Fine-tuned for dysarthric voice. Better for severe dysarthria where Standard struggles.
Text correction
Off
No correction. Raw recognition text is shown as-is. Useful for testing recognition quality.
Local (experimental)
On-device correction tuned for dysarthric error patterns. Works offline. Limited effect on severe speech.
Cloud
High-quality correction via cloud API. Requires your own API key, stored locally on your device only.
Using Cloud correction: Select Cloud, enter your cloud API key, and click Save. The key is stored locally on your device only.
Uninstall
DysVoxa can be uninstalled from within the app or via Windows Settings.
- In-app: click the trash can icon in the top-right corner, then click again within 4 seconds to confirm. The icon turns red on first click as a safety measure.
- Windows Settings: Settings → Apps → DysVoxa Free → Uninstall.
- Manual: run unins000.exe from the install directory (C:\Program Files\DysVoxa Free\).
Troubleshooting
Common issues and their solutions. For additional help, email support@dysvoxa.com.
App does not launch
Ensure your system meets the requirements. Try running as administrator. Check that your antivirus did not quarantine the executable.
No microphone detected
Verify the microphone is recognized in Windows Settings → System → Sound → Input. Try a different USB port. Restart the app after connecting.
Virtual microphone not working
Restart the app after installing VB-CABLE. In your target app, select CABLE Output (VB-Audio Virtual Cable) as the microphone input.
Cloud correction not working
Verify your cloud API key is saved and has sufficient credits. Check your internet connection.
Speech recognition is slow
Switch to Standard mode. Close other CPU-intensive applications. Ensure at least 16 GB RAM.
Text correction makes errors
Create a voice profile with calibration phrases. Try switching between Local and Cloud correction. Cloud generally performs better for dysarthric speech.
Ready to start?
Request beta access or watch the demo videos to see DysVoxa in action.