WebKit

 Introducing the Smallant (Speedrunner) (300 Epochs), an advanced AI Voice Model trained using Retrieval-Based Voice Conversion (RVC) technology. This unique model has been specifically designed to excel in creating realistic text-to-speech and AI covers of your favorite music. With extensive training data including 30 seconds of singing and approximately 10 minutes of conversational speech during a Mangio-crepe session, Smallant (Speedrunner) (3

Trained on 30 seconds of singing and ~10 minutes of talking Mangio-crepe with a hop length of 128 examples:

Smallant (Speedrunner)

Description

Samples

SimpleFlips (Speedrunner/Streamer)

Smallant (Larger Dataset)

Literally Sweaty Speedrunner Meme (REUPLOAD)

Smallant