Apple Introduces Groundbreaking Voice Cloning Feature, 15-Minute Voice Replication Now Possible

Apple has unveiled a groundbreaking feature called Personal Voice, which enables users to clone their own voice in a mere 15 minutes. This innovative addition is part of Apple’s extensive Accessibility Features portfolio, set to be made available on iOS, iPad OS, and Mac devices later this year.

The tech giant announced the arrival of Personal Voice through a blog post, describing it as a simple and secure method to create a voice that closely resembles the user’s own. Primarily aimed at individuals at risk of losing their speech capabilities, this feature will prove especially valuable for those recently diagnosed with ALS (amyotrophic lateral sclerosis) or similar ailments.

But how does Personal Voice work? By leveraging on-device machine learning, this feature ensures utmost privacy and security while enabling users to develop a voice that faithfully captures their unique vocal characteristics. Users will read a series of randomized text prompts on their iPhone or iPad for approximately 15 minutes to create their Personal Voice. Additionally, Personal Voice will integrate with the Live Speech feature, allowing users to have their own voice play during calls by simply typing a text prompt.

Explaining the Live Speech feature further, Apple stated, “With Live Speech on iPhone, iPad, and Mac, users can type what they want to say to have it be spoken out loud during phone and FaceTime calls as well as in-person conversations.”

Anticipation surrounds the imminent launch of these accessibility features, with widespread speculation suggesting their inclusion in the highly anticipated iOS 17, potentially to be announced at the forthcoming WWDC 2023 event.