Description
So, the dataset consists of the output of a bunch of ai voices, 10 to be exact, 2 minutes for each model. they add up to 20 mins of total dataset (the limit). Here are the models and creators that I combined R.O.B. (Super Smash Bros. Ultimate) [Jay] Fire In The Hole! (Cartoon Pirate Pack) [roccoarthurmckay] Drake (Kendrick Diss Era/2024) (TITAN) [gigi_clementine] SpongeBob SquarePants [ell0er] CaseOh [resizable] Super Mario (N64 Era) [Uncompressed] [trys9965] Buddy / Buddyman (Kick The Buddy 1 & 2) [Jay] V1 (Ultrakill) [Jay] Villager (Minecraft) [AI Bakery] BASS (WARNING LOUD AH) [Your_Local_Worm]
Comments
No comments yet. Start the conversation!
Add a comment
Samples
New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch