WebKit

Introducing Diggo (RVC V2) 280 Epochs, a state-of-the-art AI voice model powered by 40 minutes of carefully curated audio from YouTube videos. This versatile tool can help you generate high-quality AI music, covers, and even text-to-speech outputs without requiring attribution. Although it was initially trained using Portuguese content ('mangio-crepe'), its capabilities extend far beyond this specific genre. Experience impressive results across various applications and take your creativity to new heights! Don't miss out – try creating AI covers and transforming your texts into engaging voices with our FREE AI tools today.

< Trained with +- 40minutes of audio, isolated from youtube videos. You might need to increase hop lenght in order to prevent extreme pitch changes. It's works better with mangio-crepe. No credit needed. PT-BR: Treinado com aproximadamente 40min de audio, isolado dos videos do youtube. Talvez voc precise aumentar o hop-lenght do mangio-crepe para evitar mudanas repentinas de tom. Funciona BEM melhor com mangio-crepe. Nao precisa creditar.

Diggo

Description

Samples

Rodrigo Carvalho (Diggo)

Rodrigo Carvalho - Diggo - diggo_carvalho

Rodrigo Carvalho (Diggo)