Apple Expands Machine Learning Audio Tools to Third-Party Apps

Published by Shivani Bhore on

Apple AI audio

Apple is expanding its AI-powered Audio Mix feature, which was previously exclusive to the Photos app, to third-party apps with iOS 26 and macOS Tahoe. With this development, users of the iPhone 16 and Mac will be able to take use of improved machine learning-based audio editing capabilities, which will make video soundtracks more comprehensible and adaptable for a greater variety of applications.

Key Features of Apple’s AI-Powered Audio Mix in macOS Tahoe and iOS 26

Standard: Plays the recorded audio in its original form.

In-Frame: Minimizes voices and noises coming from sources that are not visible in the video frame.

Studio: Reduces reverb and background noise to produce a polished studio-like quality.

Cinematic: Uses surround sound to simulate movie sounds and front-facing tracks for vocals.

Apple is adding more Audio Mix choices for background noise in iOS 26.

Spatial Audio, which is automatically turned on while shooting video on all iPhone 16 versions, is required in order to use this feature.

iOS 26 gives third-party apps access to Apple’s AI-powered Audio Mix functionality, enabling programmers to incorporate sophisticated audio editing capabilities into their apps. With machine learning technology, users may further manage the audio in videos by modifying these settings straight from the Camera section of the Settings app.

By extending its Audio Mix capabilities to third-party Mac programs with macOS Tahoe, Apple is giving Mac users access to powerful audio editing on par with iPhones. Furthermore, Apple is improving audio-only applications such as Voice Memos by adding support for the QuickTime Audio (QTA) format, which offers features akin to Spatial Audio and supports multiple audio tracks and alternate track groups.