Science & Technology

Insanely realistic new AI voice is indistinguishable from a human

By T.K. Randall
March 5, 2025

Image: AI-generated (Midjourney) It wasn't that long ago that artificial intelligence still seemed like some distant futuristic technology, yet over the last few years we've seen AI advance in leaps and bounds beyond our wildest expectations.

One of the most noticeable things that has benefited from advances in AI is computer voice generation - something that was really rather limited until the advent of ChatGPT.

Gone are the monotone, Hawking-like computer voices capable only of direct responses to basic question and keywords - now we have conversational AI that feels like talking to a human.

Even that pales in comparison, however, to a brand new AI voice that technology firm Sesame revealed this week.

Designed to come across as authentic as possible, the AI can simulate every little nuance of human speech and sounds totally indistinguishable from a real human.Not only does it add emotion to its responses, but it can pause, use "umms" and "errs", and you would be extremely hard pushed to tell that you were talking to a machine.

"At Sesame, our goal is to achieve 'voice presence' - the magical quality that makes spoken interactions feel real, understood, and valued," Sesame writes on its blog.

"We are creating conversational partners that do not just process requests; they engage in genuine dialogue that builds confidence and trust over time. In doing so, we hope to realize the untapped potential of voice as the ultimate interface for instruction and understanding."

You can watch a video of someone trying it out below.

If you are feeling brave enough, you can even talk to the live demo - here.


Source: Ars Technica

Tags: Artificial Intelligence