domains / families / software-engineering / speech-recognition

speech-recognition

separate

Transcribe speech to text using Apple's Speech framework. Use when implementing live microphone transcription with AVAudioEngine, recognizing recorded audio files, handling speech and microphone authorization, choosing on-device vs server-backed SFSpeechRecognizer behavior, or adopting SpeechAnalyzer, SpeechTranscriber, DictationTranscriber, AssetInventory, and async result streams on iOS 26+.

When to use

• live microphone transcription
• recognizing recorded audio files
• speech and microphone authorization
• on-device vs server-backed SFSpeechRecognizer behavior
• adopting SpeechAnalyzer
• adopting SpeechTranscriber
• adopting DictationTranscriber
• adopting AssetInventory

When not to use

• text analysis
• language identification after transcription
• sentiment
• embeddings
• translation
• audio playback UI
• summarization over transcripts
• generation over transcripts

Skill page

Source