AI tool can clone ANYONE'S voice – try it yourself

Ever wanted to hear Donald Trump speaking Hindi or David Attenborough chatting in German? Try the AI tool that can clone anyone’s voice and make them say ANYTHING in multiple languages

  • ElevenLabs software translates voices while maintaining the speaker’s tone
  • It can clone voices in addition to creating entirely new ones never spoken before
  • Here’s how to try it yourself with your own voice or your favourite celebrity’s 

He has one of the most instantly recognisable voices in Britain, but have you ever wondered what David Attenborough would sound like speaking German?

Well, now you can find out, thanks to a new AI tool that can clone anyone’s voice and make them say anything in multiple languages. 

The tool, by ElevenLabs, requires just a few seconds of audio, and even maintains the speaker’s original tone of voice.

Creators hope this will ‘expand the horizons’ in numerous fields including publishing, game development and the media.

You can try it yourself on ElevenLabs’ website using your own voice or that of your favourite celebrity!

ElevenLabs software translates voices while maintaining the speaker’s tone of voice

HOW TO TRY THE VOICE CLONING TOOL YOURSELF 

To try out the tool for yourself, head on to the ElevenLabs website. Here, you can sign up for a free account or pay for more options.

ElevenLabs tweeted: ‘Introducing Eleven Multilingual v1: Our New Speech Synthesis Model! We’re thrilled to launch our new model supporting seven new languages: French, German, Hindi, Italian, Polish, Portuguese, and Spanish. 

‘This advancement expands the horizons for creators, game developers, and publishers, and it paves the way for using generative media to create more localized, accessible, and imaginative content.’

Twitter was flooded with comments following the announcement, with users testing the software on different famous faces.

Donald Trump was among those toyed with as ElunaAI translated what appeared to be a clone of his voice saying he had ‘never caused any controversy’.

Meanwhile, another user switched David Attenborough’s voice to German as the BBC presenter spoke on the potential of AI.

‘With this tool, anyone can do it,’ the Twitter user said. ‘Also important to note that scammers are definitely going to abuse this one.’

ElevenLabs claims that its model was built to grasp the emotion and logic behind words to create natural-sounding and convincing audio.

While it can clone voices from provided samples, the model also has the ability to create completely new voices from scratch that have never been spoken before.

Some numbers and symbols may currently be pronounced incorrectly, ElevenLabs has said, but it is working to improve these. 

The US-based firm believes its tool will prove useful in a number of different industries from education to the media. 

It said: ‘Game developers and publishers can create immersive, localized experiences for international audiences, transcending language barriers and connecting with players and listeners to maximize engagement and efficiency, at no loss to quality or accuracy.

‘Educational institutions now have the means to produce audio content for various users in their target languages, bolstering language comprehension and even pronunciation skills, as well as catering to different teaching styles and learning needs.’

Audiobook and content creators were also among those who may find it useful, thanks to the model’s ability to create unique character-like voices.

ElevenLabs added: ‘Accessibility institutes can now further empower people with visual impairments or learning difficulties by providing them with means to easily convert less accessible resources to a medium that suits their needs, both in content and form.’

Creators hope this new technology will ‘expand the horizons’ in numerous global industries

The new model can clone voices in addition to creating entirely new ones never spoken before

READ MORE: Apple quietly launches a selection of audiobooks read by an AI ROBOT 

Robot readers: Apple has launched a catalogue of books that are narrated by artificial intelligence

Later this year, ElevenLabs hopes to give users full control over the created voice, allowing adjustment of pacing and the insertion of pauses.

‘Our panel is there to help make your vision a reality,’ ElevenLabs added.  

Despite its advantages, ElevenLabs’ launch comes amid numerous concerns surrounding the wave of new voice cloning technology.

Last month, an anonymous TikTok user, @ghostwriter977, went viral after uploading an AI-generated Drake song featuring The Weeknd. 

It raised questions over the grey area of AI-made music and whether it is an infringement of copyright. 

Even so, ElevenLabs claims it is ‘fully committed’ to respecting the rights of creators in the midst of its technological advances.

It said: ‘At Eleven, we believe that we should strive to make the most of new technologies, but not at all cost. 

‘As we develop them, we make every effort to implement appropriate safeguards which minimize the risk of harmful abuse. With this in mind, we’re fully committed both to respecting intellectual property rights and to actioning misuse.’ 

MailOnline has approached ElevenLabs for comment.  

Source: Read Full Article