Fact · Accessibility and health
Apple's Listen for Atypical Speech, announced in May 2024, uses on-device machine learning to recognize a user's speech patterns and is designed, with Vocal Shortcuts, for people with acquired or progressive conditions that affect speech, such as cerebral palsy, ALS or stroke.
Checked against its source on October 16, 2026
In the source's own words
“Listen for Atypical Speech uses on-device machine learning to recognize user speech patterns. Designed for users with acquired or progressive conditions that affect speech, such as cerebral palsy, amyotrophic lateral sclerosis (ALS), or stroke, these features provide a new level of customization and control”
Apple announces new accessibility features, including Eye Tracking, Music Haptics, and Vocal Shortcuts, Apple Newsroom, 2024, New Features for a Wide Range of Speech.
Open the original- What it measures
- Announced on 15 May 2024 for iOS 18 and iPadOS 18 together with Vocal Shortcuts, which let users assign custom utterances that Siri can understand to launch shortcuts and complete tasks.
- What it does not show
- A press release: it states the design goal and does not report how much accuracy improves. The setting improves Siri and voice commands; it is not described as a full custom dictation model.