Have you checked out David Guetta’s latest DJ gig that’s been blowing up on social media? The highlight was definitely when Eminem’s signature rap hit the speakers as the opener.
But hold up, this wasn’t a live performance by Slim Shady himself. It was actually a pre-recorded sample generated by A.I. Yup, you heard that right!
Guetta used tech to create a virtual Eminem and even wrote the lyrics with the help of some artificial intelligence tools.
While we don’t have the scoop on the exact tools he used, some digging got us close to the answer.
Here is all you need to get started.
Generating the lyrics
If you haven’t been living under a rock, you are probably familiar with ChatGPT. This is an open-source A.I. tool developed by OpenAI, a research lab founded by Elon Musk and Sam Altman.
ChatGPT is a natural language processing (NLP) model that can generate text based on the input it receives. Guetta likely used this tool to generate the lyrics for his Eminem rap.
Keeping in mind that it’s all about the right prompt, a quick “Write me a few lyrics about future rave in the voice of Eminem” got some pretty decent results. In fact, we are not sure how Guetta ended up with such mediocre results. 😉
Generating the audio
Once he had the lyrics, Guetta, or someone on his team, likely used a text-to-speech (TTS) tool to generate the audio.
The Eminem voice text-to-speech on Uberduck.ai is one of the best we’ve encountered. Hearing sentences spoken in the voice of our favorite characters were incredibly realistic and truly amazing.
On Uberduck.ai, you can find a variety of character voices, including an incredibly realistic Eminem voice.
To generate these voices on Uberduck.ai, you need to sign up with your email, discord, or google account.
Once you have signed up, you can use the text-to-speech feature to generate your own Eminem rap. All you need to do is type in the lyrics and select the Eminem voice. The A.I. will then generate a realistic rap in the voice of Eminem.
We used the “All Eras” Eminem to get our sample. Unfortunalty, sharing it here is currently not supported by Uberduck.
“Use FakeYou deep fake tech to say stuff with your favorite characters.”
This app has less of a SAS feel to it, but it passed our Eminem test just as well. What we especially liked about this site is that it gets straight to the point, without the need to sign up for an account.
Generating your text-to-speech snipped does take a little longer than with Ueberduck, but we found that to be a fair trade-off for a tool without a sign-up.
Bonus point: unlike Uberduck, FakeYou lets you easily share your creation.
We recommend using the ‘Angry Freestyle” Eminem to get closer to Guetta’s sound bite.
The app has a library of voices, including Eminem’s, and you can use it to say anything in the voice of your favorite characters.
Listen to the result we got from FakeYou.
David Guetta likely used a combination of ChatGPT and text-to-speech tools to generate the Eminem rap on his live set. We believe he used either Ueberduck or FakeYou to generate the audio, but it is only possible to know for sure with further information from Guetta himself.
Either way, you are off to a great start if you want to create your own Eminem rap. All you need is the right prompt and the right tools.