iOS 17: Learn and imitate your voice in 15 minutes

Apple announced two useful features in this year’s iOS 17 accessibility update preview: Live Voice and Personal Voice. These two features are designed to help users use the device more conveniently. The real-time voice feature will allow users to operate the device through voice input without touching the screen, greatly improving accessibility. The personal voice function is a personalized voice assistant that can provide personalized services and suggestions based on the user's preferences and habits. The introduction of these features will enable iOS 17 to have greater breakthroughs and improvements in accessibility functions, providing users with a better experience.

The real-time speech feature allows users to use the keyboard to type what they want to say, and converts the entered text into clear speech to communicate with people. This is great for people who can't speak easily and can have their iPhone help them convert text to speech. Additionally, the Personal Voice feature helps users who are unable to speak normally create voices that match their real voices.

When using the Personal Voice feature, users are prompted to read a random set of text to record 15 minutes of audio on their iPhone or iPad. Through on-device machine learning technology, an iPhone or iPad can generate a voice that sounds like the user. During the recording process, users need to place the device within a specific space 6-10 inches (approximately 15-25 cm) away to complete the recording.

During the speech generation process, Apple's neural engine will complete all data locally on the device and does not need to be uploaded to the cloud for processing. This means people don’t have to worry about their voices being stolen. In addition, Apple requires third-party apps to obtain explicit authorization from users if they want to use personal voices. Even if a third-party app is authorized, Apple will take additional protective measures to prevent the third-party app from accessing personal voices and previously recorded voice material. In this way, the user's privacy and voice data are effectively protected.

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