speech-recognition — Claude Code skill: iOS speech to text
A skill that walks your agent through speech-to-text on Apple's Speech framework, from live microphone capture to recognizing recorded files.
npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a claude-codeWhat speech-recognition does
This skill covers speech recognition in iOS apps: microphone capture with AVAudioEngine, recognition of pre-recorded audio files, permission handling, and result processing. Your agent gets working patterns instead of guessing at the API.
Two paths are documented. On iOS 26+ you use SpeechAnalyzer with SpeechTranscriber and DictationTranscriber — locale availability checks, asset installation through AssetInventory, and async result streams. For iOS 10+ targets there is SFSpeechRecognizer with callbacks. A separate section explains when on-device recognition beats the server-backed route, plus a checklist of common mistakes.
You need NSSpeechRecognitionUsageDescription and NSMicrophoneUsageDescription in Info.plist before anything runs — without those keys the system blocks both speech and microphone access. Text analysis after transcription is out of scope: language identification, sentiment, embeddings and translation go to other skills, as does audio playback UI. If your project already configures AVAudioSession itself, expect to adapt the templates, because the sample category setup will overwrite yours.
What it helps with
- build live microphone transcription on
AVAudioEngine - recognize an audio file recorded earlier
- request speech and microphone permissions with the right
Info.plistkeys - decide between on-device and server recognition for a given locale
- migrate from
SFSpeechRecognizertoSpeechAnalyzeron iOS 26+
Example prompts for the agent
- Help me set up live microphone transcription with
AVAudioEngineandSFSpeechRecognizer - How do I request speech recognition and microphone permissions on iOS?
- Move this transcription code to
SpeechAnalyzerandSpeechTranscriberfor iOS 26+
How to install speech-recognition
1Skills CLI (Vercel)
npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a claude-code2Manually: put the files in place
~/.claude/skills/speech-recognition/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/speech-recognition/
1Skills CLI (Vercel)
npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a codex2Manually: put the files in place
.agents/skills/speech-recognition/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a cursor2Manually: put the files in place
.cursor/skills/speech-recognition/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install dpearson2699/swift-ios-skills speech-recognition2Manually: put the files in place
.github/skills/speech-recognition/SKILL.md1Skills CLI (Vercel)
npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a gemini-cli2Platform CLI
gemini skills install https://github.com/dpearson2699/swift-ios-skills --path skills/speech-recognitionManually: put the files in place
.devin/skills/speech-recognition/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about speech-recognition
How do I install speech-recognition in Claude?
Run npx skills add dpearson2699/swift-ios-skills --skill speech-recognition -a claude-code. The skill lands in ~/.claude/skills/speech-recognition/SKILL.md.
What does speech-recognition do?
It gives your agent patterns for iOS speech recognition: live microphone input, recorded files, authorization, and the choice between SpeechAnalyzer and SFSpeechRecognizer.
Which iOS versions does the skill cover?
SpeechAnalyzer and SpeechTranscriber target iOS 26+, while SFSpeechRecognizer covers iOS 10+. Older deployment targets keep the second option.
