The company OpenAI has introduced a new artificial intelligence-based tool called Voice Engine, which can voice texts with the voice of any person.
This is reported on the company’s website, according to Ukrinform.
The Voice Engine uses a 15-second sample of a particular person’s speech to reproduce text as he or she speaks it. The technology has been developed since the end of 2022 and initially used preset voice samples for voice-over.
Currently, there is no public access to the Voice Engine because developers fear its unscrupulous use.
“We hope to spark a dialogue about the responsible use of synthetic voices and how society can adapt to these new possibilities. OpenAI stated that based on these discussions and test results, we will make a more informed decision about whether and how to deploy this technology at scale.”
The Voice Engine is said to be the basis for the ChatGPT chatbot’s “Read Out Loud” feature.
According to the developers, this technology can be used to help children as well as those who cannot read; to translate videos and podcasts; to help restore the voice of patients with sudden or degenerative disorders of the speech apparatus. Additionally, the Voice Engine can enable voiceless people to communicate.
Examples of using the Voice Engine in each of these situations are provided on the blog.
As reported, Meta company is testing an AI-based chatbot and photo editor in the latest beta versions of WhatsApp messenger.
Photo: Gabby Jones/Bloomberg