Speech Recognition

This covers both the legacy SFSpeechRecognizer API and the new iOS 26+ SpeechAnalyzer actor-based approach for converting speech to text. You'll find working examples for live microphone transcription with AVAudioEngine, file-based recognition, and the complete authorization flow for both speech and microphone permissions. The SpeechAnalyzer section is especially useful if you're targeting modern iOS since it shows the async/await pattern with AsyncSequence results and the asset download system for on-device recognition. The side-by-side comparison table makes it clear when to use which API. Good reference for avoiding the common AVAudioEngine tap setup mistakes and understanding the difference between server and on-device recognition modes.

skills.sh installs: 3.8K
GitHub stars: 1.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add dpearson2699/swift-ios-skills --skill speech-recognition --agent claude-code

Installs into .claude/skills of the current project.

Files

Speech Recognition

Transcribe live and pre-recorded audio to text using Apple's Speech framework. Covers SpeechAnalyzer / SpeechTranscriber (iOS 26+) and SFSpeechRecognizer (iOS 10+) fallback guidance.

Scope boundary: Use this skill for speech-to-text recognition, speech authorization, microphone capture plumbing, and result handling. Hand off text analysis, language identification after transcription, sentiment, embeddings, and translation to natural-language; hand off audio playback UI to avkit; hand off summarization or generation over transcripts to apple-on-device-ai.