AI TTS Voice Cloning

AI TTS Voice Cloning lets you generate Text-To-Speech audio using a clone of your own voice - or any voice you have permission to use. Instead of a generic AI voice, your stream can speak in a voice that actually sounds like you.

Once your voice is cloned, it can be used across multiple PotatoHotDog features, including the Automatic Chat Reader and Channel Point TTS Browser Sources.

How It Works

Cloning your voice takes just a few steps:

• Record a short audio sample of the voice you want to clone (10 to 60 seconds).
• Upload the WAV file to your PotatoHotDog dashboard.
• Select the language the voice is spoken in.
• Give the cloned voice a name so you can identify it later.
• Your cloned voice is now available to use in any compatible PotatoHotDog feature.

Audio Requirements

For the best cloning results, make sure your audio sample meets these requirements:

• WAV format only.
• Maximum 10 MB in size, between 10 and 60 seconds in duration.
• Use as clean audio as possible - no background noise, music, or echo.
• Include as many phonetic variations as possible for a more accurate clone.
• Only upload voices you have permission to clone.

Supported languages are English, German, Portuguese, Italian, and Spanish.

Get Started

Log in to your PotatoHotDog account and upload a voice sample to create your first cloned voice.