ElevenLabs Becomes Frighteningly Good at the Art of AI Impersonating Voices
In Brief
Neural networks are the future of technology, and the latest update to ElevenLabs Neuron allows it to do something even more impressive: impersonate anyone’s voice.
The synthesizer was released in beta at the end of January, and a week later, the Internet was flooded with audio fakes featuring the voices of famous people.
ElevenLabs has promised to deal with fakes and rebuild the algorithm.
Some people say that neural networks are the future. They can do things faster than humans and even achieve things humans can’t. But what if they could do something even more impressive, like impersonate anyone’s voice? That’s what the latest update to ElevenLabs Neuron allows it to do, and it’s pretty much the coolest thing ever.
| Recommended post: Top 120+ AI Generated Content in 2023: Images, Music, Videos |
If you’ve ever wanted to sound like Tony Stark or Steve Jobs, now you can. Or if you’re feeling extra ambitious, you can even impersonate Kim Kardashian. All you need is a minute-long sample of someone’s voice, and AI will do the rest. So if you’re looking to impress your friends with your spot-on celebrity impressions or just want to have some fun experimenting with different voices, it’s sure to be a blast.
Of course, some beta users start to use it in creepy experiments. There have been some reports in the community saying some pretty creepy things, like when the bot was asked to read a passage from one of the Harry Potter books in Emma Watson’s voice, it instead provided a passage of “Mein Kampf” read by the Harry Potter franchise star. But overall, it’s an impressive feat of technology, and it will only get better from here.
| ElevenLabs, a startup, released the synthesizer into beta at the end of January. And a week later, the Internet was flooded with audio fakes featuring the voices of famous people: Joe Biden, Margot Robbie, Joe Rogan, George Lucas, Emma Watson, and Tom Cruise. The fact is that very short audio or video samples are enough for the service’s training. And the voices are real! ElevenLabs promised to deal with fakes and rebuild the algorithm. |
| Recommended post: 10 Best AI Marketing Tools for Effective Digital Advertising |
So if you’re looking to impress your friends with your spot-on celebrity impressions or just want to have some fun experimenting with different voices, check out ElevenLabs Neuron. It’s sure to be a blast.
- In January, Microsoft announced Vall-E, a new zero-shot text-to-speech model that can duplicate everyone’s voice. Microsoft’s VALL-E is a transformer-based TTS model that can generate speech in any voice after only hearing a three-second sample. This is a significant improvement over previous models and has the potential to change the way we interact with digital media. The code is still lacking, but Microsoft has released examples of the model in action.
- Vall-E appears to be the most dangerous scam software ever released. It is a synthetic voice that can be used to imitate real people and is made using a recording of a real person’s voice and a Microsoft code. The best part is that it requires just three seconds of speech for learning, or more precisely, for microlearning. Vall-E is dangerous because it can be used to trick vulnerable people into transferring funds to a card, and con artists can use it to impersonate someone familiar to the victim.
Read more about AI:
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Damir is the team leader, product manager, and editor at Metaverse Post, covering topics such as AI/ML, AGI, LLMs, Metaverse, and Web3-related fields. His articles attract a massive audience of over a million users every month. He appears to be an expert with 10 years of experience in SEO and digital marketing. Damir has been mentioned in Mashable, Wired, Cointelegraph, The New Yorker, Inside.com, Entrepreneur, BeInCrypto, and other publications. He travels between the UAE, Turkey, Russia, and the CIS as a digital nomad. Damir earned a bachelor's degree in physics, which he believes has given him the critical thinking skills needed to be successful in the ever-changing landscape of the internet.
More articles
Damir is the team leader, product manager, and editor at Metaverse Post, covering topics such as AI/ML, AGI, LLMs, Metaverse, and Web3-related fields. His articles attract a massive audience of over a million users every month. He appears to be an expert with 10 years of experience in SEO and digital marketing. Damir has been mentioned in Mashable, Wired, Cointelegraph, The New Yorker, Inside.com, Entrepreneur, BeInCrypto, and other publications. He travels between the UAE, Turkey, Russia, and the CIS as a digital nomad. Damir earned a bachelor's degree in physics, which he believes has given him the critical thinking skills needed to be successful in the ever-changing landscape of the internet.
