Does this skill support the latest iOS 26 APIs?

Yes, it specifically covers the new actor-based SpeechAnalyzer and SpeechTranscriber APIs introduced in iOS 26 using Swift concurrency.

How does it handle microphone permissions?

The skill provides patterns for requesting both NSSpeechRecognitionUsageDescription and NSMicrophoneUsageDescription, ensuring all necessary permissions are granted before recording.

Is it compatible with older iOS versions?

While focused on modern Swift and iOS 26, it also includes patterns for SFSpeechRecognizer, which is compatible with iOS 10 and later.

Can I use this for offline speech recognition?

Yes, it includes implementation details for on-device recognition and asset management via AssetInventory to support offline use cases.

Does it support real-time punctuation?

Yes, it demonstrates how to enable the addsPunctuation property (iOS 16+) and use contextual strings to improve recognition of domain-specific terms.

iOS Speech Recognition

Name: iOS Speech Recognition
Author: dpearson2699

bydpearson2699

•

409

•

Mobile Development

Implements advanced speech-to-text capabilities in iOS applications using the latest Apple Speech frameworks and Swift concurrency.

This skill provides comprehensive guidance for integrating speech recognition into Swift applications, covering everything from legacy SFSpeechRecognizer to the cutting-edge SpeechAnalyzer API introduced in iOS 26. It assists developers in managing complex authorization flows for both microphones and speech services, configuring on-device processing for offline use, and utilizing modern AsyncSequence patterns for real-time transcription. Whether you are building live voice-controlled interfaces or processing pre-recorded audio files, this skill ensures best practices for performance, battery efficiency, and transcription accuracy using Swift 6 concurrency.

주요 기능

01Automated handling of dual authorization for Microphone and Speech Recognition

02Configuration for on-device versus server-based recognition and asset management

03Live microphone transcription patterns using AVAudioEngine

04Implementation of advanced features like automatic punctuation and contextual strings

05409 GitHub stars

06Support for the new iOS 26+ SpeechAnalyzer actor-based API

사용 사례

01Transcribing pre-recorded audio files for content indexing or accessibility

02Implementing on-device, offline speech recognition for privacy-focused applications

03Building a real-time voice-to-text dictation feature for a productivity app

주요 기능

01Automated handling of dual authorization for Microphone and Speech Recognition

02Configuration for on-device versus server-based recognition and asset management

03Live microphone transcription patterns using AVAudioEngine

04Implementation of advanced features like automatic punctuation and contextual strings

05409 GitHub stars

06Support for the new iOS 26+ SpeechAnalyzer actor-based API

사용 사례

01Transcribing pre-recorded audio files for content indexing or accessibility

02Implementing on-device, offline speech recognition for privacy-focused applications

03Building a real-time voice-to-text dictation feature for a productivity app