Introducing the SuperMarioGlitchy4/SMG4 Mario RVC v2 Model, meticulously trained over 300 epochs at VoiceMy.ai. This unique model showcases Mario's voice from the War Of The Fat Italians rap battles, unlike previous models based on regular Mario voices. With our advanced AI technology, you can now generate AI covers and text-to-speech like never before. Try it out today and experience the difference!

There's already an SMG4 Mario model but it's trained off the spliced voice lines he uses which is literally just regular Mario so for this I specifically used his voice from the War Of The Fat Italians rap battles.

Mario (supermarioglitchy4 / SMG4), Trained

Mario (supermarioglitchy4 / SMG4) - RVC v2, 300 Epochs, VoiceMy.ai Trained

xhepyxopila

2 tips I have for this model if you use it

2. Sing the song yourself with Marios italian accent if you can cause otherwise he barely sounds like Mario

here's what it sounded like when I used the default Ballin acapella

The singer from those hilariously bad McDonalds Happy Meal ads from Pakistan. Trained off singing data from the Crash Bandicoot Sonic and Play Doh ads minus parts with backing vocals. 500 epochs RMVPE TITAN pretrain.

Pakistan McDonalds Ad Singer

Trained off voice lines from Wonder and NSMB U since they were the clearest quality. 300 Epochs OV2 pretrain.

Kamek (Super Mario Franchise, Wii U / 3DS / Switch Era)

Trained off the uncompressed voice files for Star Fox 64 originally found in the 2020 Nintendo gigaleak. Model uses TITAN pretrain with 300 Epochs. Also I made a mistake and forgot to generate an index before training so uhh I have no clue if doing it after training makes a difference.

Falco Lombardi (Star Fox)

Haven't tested yet but this should theoretically be my best Birdo model to date. Dataset used is Mario Kart 8 Deluxe BCP since it has her lines in the highest quality DeEcho'd and DeVerb'd so the results aren't weirdly robotic sounding RIN-E3 pretrain and 300 epochs.

Birdo (Super Mario Franchise) - The Final Model

Trained off 2 minutes of data with RIN-3 pretrain

Brian Griffin (Family Guy)

SMG4

SMG4 (RVC V2, Crepe, 250 Epochs)

nibi_1

My most ridiculous model yet. Dataset was 1:00 (8.6 seconds repeated). Hurt noises were included so you will hear hitting noises often.

Villager (From Minecraft)

Villager (From Minecraft) (RVC v2) 500 Epoch

analogspiderweb

after many failed attempts I've finally done it mario's voice from sm64 now has a rvc model yeah i was abit curious to see what 64 mario could sound like if it had a rvc model and now here we are dataset and trained by me not sure if this would sound good in most songs but yea enjoy ig <

Mario (From Super Mario 64)

Mario (From Super Mario 64) (RVC v2) 150 Epochs

SJ64

300 Epochs. Voice clips from Team Sonic Racing and Sonic Twitter Takeover 5 & 7 used to make up this model. If you can it's recommended that it's used with the AI Cover Gen WebUI for male/female pitch adjustment depending on how high pitched or low pitched a song is.

Mario (supermarioglitchy4 / SMG4), Trained

Description

Add a comment

SMG4

Villager (From Minecraft)

Mario (From Super Mario 64)

Sonic The Hedgehog [Roger Craig Smith]

Saiba Momoi (Blue Archive)

Villager (Minecraft)

Sas (Counter-strike global offensive)

FIXED HATSUNE MIKU V3 - VOCALOID [SCROLL DOWN FOR LINK]

Fang [Brawl Stars]

Ariana Grande AI

JP Furina / Focalors CV: Inori Minase (Genshin Impact)

Mortis [Brawl stars]

Jungkook (BTS)

ENHYPEN Heeseung

Miss Circle (Fundamental Paper Education)

CaseOh

Takanashi Hoshino (from Blue Archive)

Surge (brawl Stars)

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

SpongeBob SquarePants (Talking And Singing)

Melodie - (Brawl Stars) - (English & Korean Voices)

Sonic The Hedgehog [Roger Craig Smith]

Jay (ENHYPEN)

Satoru Gojo (JJK) [VA Yuichi Nakamura]