OpenAI’s new tool can clone your voice with 15 second voice sample

Created in late 2022, Voice Engine is currently powering preset voices in text-to-speech programmes such as Read Aloud and ChatGPT Voice...

Digital Desk: Voice Engine is a new technology that OpenAI has been developing. The tool's functionality is highly contentious and, if disclosed publicly, might provide some security issues. An artificial intelligence tool called Speech Engine can copy a speech sample in just 15 seconds after listening to it. That is to say, after listening to it for a brief while, it can still produce the same voice. One of the main explanations for why OpenAI hasn't released the feature to the public yet is this.

The company's announcement of Voice Engine, which hints at its intention to advance voice-related technology, follows the filing of a trademark application for the moniker. OpenAI has chosen to restrict Voice Engine's availability to a small number of early testers for the time being, citing worries over potential misuse and the accompanying risks, despite the technology's potentially revolutionary potential.

Created in late 2022, Voice Engine is currently powering preset voices in text-to-speech programmes such as Read Aloud and ChatGPT Voice. OpenAI is cautious about making it broadly available, though, as there's a chance that individuals could abuse artificial voices. They want to discuss how society can accept these new skills and how to use synthetic voices responsibly. 

To determine whether and how to expand the use of this technology in the future, they will consider input from these discussions as well as the outcomes of their experiments.