iPhone 17 innovative feature: Learn and imitate your voice in just 15 minutes

As part of this year’s preview of iOS 17 accessibility updates, Apple announced two useful features: Live Voice and Personal Voice.

Among them, real-time voice allows users to input what they want to say through the keyboard, converting the input text into clear voice to communicate with people, which is inconvenient to speak. If so, you can ask your iPhone to speak it for you. The personal voice function helps users who are unable to speak normally create their realistic voices.

When using personal voice, the user will be prompted to read a set of random text prompts to Record 15 minutes of audio on your iPhone or iPad. Then using on-device machine learning, the iPhone or iPad can create a voice that sounds like them. During the recording process, users need to complete the recording in a specific space 6-10 inches (approximately 15-25 cm) away from the device.

## Regarding the issues that people may be worried about about sound being stolen, in fact during the generation process In , all data will be completed locally on the device through Apple's neural engine, and there is no need to upload it to the cloud for processing. After speech synthesis, if third-party applications want to use personal voices, they must obtain explicit authorization from the user. Even when third-party applications are authorized for use, Apple will use additional background protection to ensure that third-party applications cannot obtain personal voices and voice materials previously recorded by users.

The above is the detailed content of iPhone 17 innovative feature: Learn and imitate your voice in just 15 minutes. For more information, please follow other related articles on the PHP Chinese website!