See it in action.
From download to your first sentence in a few minutes.
Made for real conversations.
Live, not recorded.
Speak, and the other side hears the new voice about a second later. Built for calls, streams and games.
Serious hardware. None on your desk.
The voice model runs on a dedicated cloud GPU rented for your session, so an ordinary laptop is all you need.
Closer with every voice.
Fine-tune a voice from ten minutes of clean recordings for an even closer match.
Consent comes first.
Use only voices whose owners have agreed. Impersonating anyone without permission is against our terms.
Four steps. That’s it.
Pay for minutes, not months.
No subscription. Top up with Kaspa, and your time stays on your account until you use it.
Time counts only while your voice server is ready and running. The start-up warm-up is free.
What you need.
Questions, answered.
Do I need a powerful computer?
No. The heavy work happens on a cloud GPU. You need a microphone, headphones and an internet connection of about 250 kbit/s each way.
How is my time counted?
From the moment your voice server is ready until you stop it. The few minutes it takes to start are free, and the app shows a live countdown.
How do I pay?
With Kaspa (KAS). The app shows a QR code and an exact amount. Send exactly that amount from a Kaspa wallet: paying straight from an exchange can change the amount.
Will I sound exactly like the other person?
You take on the colour of the chosen voice. Your accent, rhythm and intonation stay your own, which is why it sounds natural in conversation.
Can I use it in Discord, OBS or Zoom?
Yes. Choose “Virtual microphone” in the app, then select it as the microphone in your other app. On Windows this needs the free VB-CABLE driver.
Windows says it protected my PC.
Windows shows this for new apps that are not yet code-signed. Choose More info, then Run anyway. You can check the file against the SHA-256 shown on this page.
Which voices may I use?
Only voices whose owners have agreed. The app asks you to confirm consent for every voice you add.