Cloning your voice in 15 seconds is not science fiction, this is what OpenAI has just presented

NinFan

Cloning your voice in 15 seconds is not science fiction, this is what OpenAI has just presented

artificial intelligence, Cloning, fiction, News and Updates, OpenAI, presented, science, seconds, Spain, voice

Artificial intelligence has become one of the tools of the moment, in part thanks to its versatility. We have seen AI capable of creating images, videos and 3D elements. Tools have also been created that can clone a person’s voice, but in this area OpenAI has taken a big step forward.

The company led by Sam Altman has published an article in which it presents Voice Engine, an artificial intelligence engine capable of create a digital clone of a human voice from a simple short 15 second audio clip. In this way, it is possible to transfer texts to voice recordings without human intervention.

Voice Engine is not new, and It has been used by OpenAI itself since 2022 in functions such as the ChatGPT voice system. What’s new is the ability to create new voices simply from a small audio file of a person.

The dangers of digital voice

OpenAI itself has made it clear that it is a tool under development and stands out for the simplicity of its creation. However, they also recognize that are aware of the problem with this type of toolbecause it is very easy to use them to create disinformation on a level that many people would not yet be able to distinguish.

In fact, this is exactly what stopped this feature from being available yet. OpenAI is currently investigating how to make its use less problematic, and until it finds a way, it won’t be a freely accessible feature.

The advantages of digital voice

But these are not all problems. Among the uses highlighted by the company are: helping people with some type of reading difficulty texts or when teaching children. The naturalness of the voices created is one of its strong points.

It also has a very useful for translating and learning new languages. The created voices not only work in the language in which they were trained, but can also be used to read or speak in other languages, while retaining the characteristics of said voices.

Currently, OpenAI is working with some companies and developers who are proposing different uses and giving feedback. Of course, they are prohibited from creating tools that allow users to create their own voices. This is purely for security reasons, especially in a year where there are so many elections like this.

Leave a Comment