Technology

Artificial Intelligence can now clone your voice & you cannot differentiate it

The Canadian AI start-up Lyrebird has managed to develop an AI platform that is capable of mimicking anybody’s voice by just listening to an audio clip of less than one minute.

As reported by their website, the Montreal-based AI company aims to “create the most realistic voices in the world.”
Last month in June, Bloomberg interviewed the founders of Lyrebird and they claimed to have built a software that is capable of cloning any voice after listening to it for less than a minute.

The technology has already helped many people in the past including Pat Quinn, the founder of the Ice Bucket Challenge who lost his mobility and speech after being suffered from a disease called motor neurone disease. The disease eventually took his voice. This is where Lyrebird voice algorithm came into rescue. The company used the video clips of Quinn’s speeches to replace the text-to-speech robotic voice Quinn previously used to communicate.

Voice replication can be fun but sometimes it becomes creepy and risks of potential misuse of the technology are always present. According to the Verge, by using neural networks, Lyrebird has also cloned the voices of President Donald Trump and former President Barack Obama with a relatively small number of voice samples.

The startup is well aware of the unpleasant and illegal things that could occur due to the duplication of voices. They say “This could potentially have dangerous consequences such as misleading diplomats, fraud, and more generally any other problem caused by stealing the identity of someone else.”

Jose Sotelo, co-founder of Lyrebird, said in a video:

“We want our technology to be used for positive things, It’s not something that we should be afraid of. It’s something that we should be careful about and enthusiastic about.”

Lyrebird has also stated that they can add emotion into their AI’s speech, making the voice you are listening to is angry, sad, happy, stressed, and even sympathetic. Lyrebird says that this AI technology can be used for a myriad task, including the “reading of audiobooks with famous voices, for connected devices of any kind, for speech synthesis for people with disabilities, for animation movies or for video game studios.”

Sponsored
Aqsa Khunshan

I have done Mphil in Biotechnology from Punjab University, Lahore. I love to write about topics that fascinate me; business, startups, health, technology and, women empowerment. I am a foodie, ambivert, and angry anarchist. I have an instinct to learn new things and explore innovative ideas. You can reach out to me at aqsa.khunshan@techjuice.pk

Leave a Comment
Share
Published by
Aqsa Khunshan

Recent Posts

China’s Tencent Releases Large Language Model, Opens it For Enterprise Use

Capable of conversing in both Chinese and English, Tencent’s large language model ‘Hunyuan’ is claimed…

7 months ago

Apple Reportedly Spending ‘Million of Dollars Each Day’ for AI Training

Working on multiple AI models, Apple has allocated several teams who are working on artificial…

7 months ago

World’s Largest Wind Turbine Breaks Record For Power Generated In A Single Day-During A Typhoon

The world's largest offshore wind turbine has achieved a milestone by setting a new record…

7 months ago

YouTube Will Let You Play Mini Games Soon

YouTube is stepping into the world of gaming. YouTube has started testing out its gaming…

7 months ago

Pakistani Student Won First Position In Matric Exams of UAE

In a remarkable academic achievement, Abdullah Zaman, a Pakistani student hailing from Attock, has clinched…

7 months ago

‘Flying Bum’ World’s largest Aircraft Is Ready To Launch In 2026 With Hybrid Technology

Flying Bum, the world's largest aircraft is ready to launch in 2026. The Airlander 10…

7 months ago