Skip to main content

6 examples of how creepy and realistic AI-generated voices have become

In the ongoing AI revolution, images and text are yesterday’s news, leaving audio as a new frontier to explore, and incredible progress has already been made. Here are six examples of AI audio generation that will leave you speechless.

Twitter is a hub of AI excitement, and notable artificial intelligence curator Barsee collected 13 examples of computer audio that create music, vocals, and speech, and we’re highlighting six of those. Musicians and voice actors might be the next to face the challenge of AI encroachment.

Recommended Videos

We’ll start off with one of the most chilling examples from Barsee showing Matt Damon’s speech to the UN about climate change, but in a number of different voices.

Please enable Javascript to view this content

11labs new AI voice cloning technology is alarmingly good. pic.twitter.com/omEiuHYRf3

— Barsee 🐶 (@heyBarsee) February 13, 2023

The voice cycles between Damon’s own to that of Joe Rogan, Steve Jobs, Robert Downey Jr., Bill Gates, and Kim Kardashian. The flawless lip sync and spot-on replication of celebrity voices mean we can no longer trust our ears.

Another impersonation example takes a humorous approach, pitting President Joe Biden against former President Donald Trump in a trash-talking (and freely cursing) game of Overwatch. This example was taken from a tweet by Twitter user bug, who explained that it was made with the free voice.ai tool.

this is what ai voice generation is meant to be pic.twitter.com/VASGmKasOU

— bug (@augerbug) February 16, 2023

Next up is a somewhat obscure example from Barsee features an AI simulating Microsoft co-founder Paul Allen’s voice describing a day in the life of an internet troll while showing a photo of American Psycho star Christian Bale.

Nvidia demonstrated voice generation in 2021 — ancient history, given the rapid pace of advancement, and the process has become much easier now, managing to clone a voice with just three seconds of audio.

Perhaps the most shocking example? AI-generated vocals that impersonate popular artists. Vocals are no problem for an AI, and Roberto Nickson tweeted a snippet of a rap song that replaced his voice with Kanye’s. If you’re familiar with his voice, the impersonation really is uncanny.

And just like that. The music industry is forever changed.

I recorded a verse, and had a trained AI model of Kanye replace my vocals.

The results will blow your mind. Utterly incredible. pic.twitter.com/wY1pn9RGWx

— Roberto Nickson (@rpnickson) March 26, 2023

Adding to the fun of AI and music, Spotify recently announced it’s partnering with OpenAI to offer an AI-generated DJ that introduces songs and picks music you’ll like.

Lastly, check out this refreshing and creative use of AI that was tweeted by Tobi. The example is an intriguing short film, The Last Stand. The creators used brightpen.ai to generate dozens of voices speaking various languages reacting to first contact with aliens.

https://twitter.com/notTobi_/status/1642066827013488640

You can see the whole thread with 13 audio AI examples collected by Barsee on Twitter.

Alan Truly
Alan Truly is a Writer at Digital Trends, covering computers, laptops, hardware, software, and accessories that stand out as…
OpenAI’s Sora doesn’t feel like the game-changer it was supposed to be
Sora's interpretation of gymnastics

OpenAI has teased, and repeatedly delayed, the release of Sora for nearly a year. On Tuesday, the company finally unveiled a fully functional version of the new video-generation model destined for public use and, despite the initial buzz, more and more early users of the release don't seem overly impressed. And neither am I.

https://x.com/OpenAI/status/1758192957386342435

Read more
Google’s new Gemini 2.0 AI model is about to be everywhere
Gemini 2.0 logo

Less than a year after debuting Gemini 1.5, Google's DeepMind division was back Wednesday to reveal the AI's next-generation model, Gemini 2.0. The new model offers native image and audio output, and "will enable us to build new AI agents that bring us closer to our vision of a universal assistant," the company wrote in its announcement blog post.

As of Wednesday, Gemini 2.0 is available at all subscription tiers, including free. As Google's new flagship AI model, you can expect to see it begin powering AI features across the company's ecosystem in the coming months. As with OpenAI's o1 model, the initial release of Gemini 2.0 is not the company's full-fledged version, but rather a smaller, less capable "experimental preview" iteration that will be upgraded in Google Gemini in the coming months.

Read more
ChatGPT unveils Sora with up to 20-second AI video generation
An AI generated image of a woman who walks the streets of Tokyo.

OpenAI has been promising to release its next-gen video generator model, Sora, since February. On Monday, the company finally dropped a working version of it as part of its "12 Days of OpenAI" event.

"This is a critical part of our AGI roadmap," OpenAI CEO Sam Altman said during the company's live stream.

Read more