Free beta
Record a phrase when you choose, the app transcribes it to text locally, optionally corrects recognition errors common in dysarthric speech, and speaks it aloud through your speakers or communication apps such as Zoom. The current focus is DysVoxa Free, a privacy-first beta.
Tens of millions of people worldwide live with dysarthria. Their thoughts are clear, but their speech muscles don't cooperate. Words come out slurred, slow, or hard to understand. Conditions like stroke, Parkinson's, ALS, cerebral palsy, and ataxia can all cause it.
The real cost goes beyond being hard to understand. After enough failed conversations — repeating yourself, being misheard, having someone else speak for you — many people start avoiding calls, group settings, and conversations unless they have no choice. Communication breakdown leads to isolation.
I built DysVoxa because I needed it myself. After being diagnosed with spinocerebellar ataxia, everyday communication started feeling like an obstacle: repeating myself on calls, losing momentum in conversations, watching routine interactions become tiring. My mobility is now significantly limited — which makes reliable remote communication matter even more.
As a technologist, I approached that as an engineering problem: reduce the communication breakdown, measure what works, and keep iterating until the system becomes useful in daily life. That's what DysVoxa is.
— Igor, Founder
Research on dysarthria consistently shows that the problem isn't just being hard to understand — people withdraw. They stop speaking up: avoiding calls, appointments, conversations they would otherwise have. DysVoxa is not therapy and not a cure. But if it helps someone stay in one more phone call, one more appointment, one more conversation they would otherwise avoid — that's the point.
1. Record
You choose when each phrase starts and stops.
2. Understand
Transcribes your speech to text locally on your PC — no audio sent to any server.
3. Refine
Optionally cleans up the transcript locally — shaped by dysarthric speech data, and guided by your voice profile if you've created one.
4. Speak
Reads the result aloud with natural text-to-speech, routed to speakers, a virtual microphone, or both.
Built for impaired speech
Not repurposed dictation software. Designed from day one for speech that standard tools fail to recognize.
Correction built for dysarthric speech
Its local text cleanup is shaped by transcripts of impaired speech, so it is aimed at the kinds of recognition errors dysarthric speakers actually run into.
Privacy-first
Speech recognition and voice output run entirely on your computer. Biometric voice data and audio never leave your device. In the current beta, there is no telemetry or behavior tracking.
Voice profile steers correction around your personal misrecognition patterns
Create a voice profile and DysVoxa uses it to steer correction around the ways your speech tends to be misrecognized, so the same mistakes are handled more intelligently over time.
Guided setup, single application
One desktop app with everything built in. Lists what's installed, what's missing, and downloads required components. No command line, no manual file copying, no servers to configure.
Uses your natural speech
Not a symbol board or pre-programmed phrases. You speak naturally and DysVoxa makes it clearer.
DysVoxa Free is the current beta. DysVoxa Pro is planned as the later paid tier, with more personalized speech support and the revenue that keeps the project alive.
Free
Pro
This Free/Pro structure keeps the beta accessible now while creating a realistic path to keep the project going.
Now: donations keep the beta moving
Donations fund the hardware, testing, operating costs, and day-to-day work needed to keep DysVoxa moving toward a public release.
After the goal: stretch funding extends the project
The stretch range is an extra €5,000 to €5,500 for added polish and expansion after the core campaign is funded.
Tens of millions affected
Dysarthria is one of the most common and least-served speech conditions worldwide
Working beta
Your support turns it into a reliable public release
No server ever sees your voice
Speech recognition and text-to-speech run locally on your device, by design
DysVoxa is a working Windows desktop app. The core loop — record, understand, refine, speak — already works in the current beta and has been tested with ataxic dysarthria.
What works now
What's planned for Pro
DysVoxa Free is a Windows desktop application currently in beta. To try it, email support@dysvoxa.com to sign up for the beta program.