YouTuber Uses AI to Create a Fake Nirvana Song

Funk Turkey, a YouTuber with 40 thousand subscribers, has just made a song a fake Nirvana song called ‘Smother’ using nothing but Artificial Intelligence.

The YouTuber applied the same trick, using a bot to write lyrics to create other fake songs as well by AC/DC, Nickelback, Metallica, and even Red Hot Chili Peppers. Respectively, these are named Great Balls, Nickelbot, Deliverance Rides, and Tool Shed.

Nirvan AI

Nirvan AI

In the official video of Smother uploaded to YouTube, Funk Turkey explains the following in the attached description:

Using to scrape the Genius Lyrics Database, I made a Markov Chain write Nirvana lyrics. This is the end result- “Smother”.

Evidently, he has made quite a following through these pseudo songs using a bot called Markov Chain, which is known to produce brilliant imitations of a renowned person’s style. What it really does is take a good amount of statements and sentences that this specific person has said, and form, or at least try to, various possibilities based on those statements.

Anyways, after writing down the lyrics attained from the Markov Chain, Funk Turkey says, “All music/vocals performed, mixed, and mastered by me, in my kitchen, on a sparkly red cheap Stratocaster, a crappy mic, and an old copy of ProTools.”

“I know Dave Grohl hates computer drums, but it’s the best thing I got, soooo… Sorry, Dave. I still love you.”, the YouTuber said upon using “Super Drummer 2” to optimize his drum settings.

Moreover, Funk Turkey says,

Vocals are doubled, slightly compressed, and run though an emulated reel-to-reel and tube saturation for a bit of extra warmth and grit. Also the first use of my new pop filter that my wife bought me for early father’s day. She’s the best.

Nevertheless, some of the lyrics in the video don’t exactly see eye to eye with the actual grace of  Nirvana. “‘Hey, wait! I got a mosquito / In all we are is all is gay.” 

Viewers can check out the latest creation of Funk Turkey themselves below:

You may also like

Leave a Comment

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More