skills.rest
onymchat
onymchatOFFICIAL
Explore all skills by this author →
GitHub

speech-recognition

Transcribe live and pre-recorded audio using Apple's Speech framework.

Updated Apr 30, 2026
Search Tags:#authorization#transcription#ios#speech-recognition#sfspeechrecognizer#speechanalyzer
One-click install
npx skills add https://github.com/onymchat/onym-ios --skill speech-recognition-onymchat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech-recognition
Source: https://github.com/onymchat/onym-ios/tree/main/.claude/skills/speech-recognition
Command: npx skills add https://github.com/onymchat/onym-ios --skill speech-recognition-onymchat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe live and pre-recorded audio to text using Apple's Speech framework, enabling apps to convert speech into searchable, accessible transcripts.

Core Features & Use Cases

  • Live Microphone Transcription: Real-time speech-to-text from AVAudioEngine input.
  • Pre-Recorded Audio File Recognition: Transcribe audio files for offline or server-based processing.
  • iOS 26+ Opt-in: Use SpeechAnalyzer for modern async/await workflows, otherwise fall back to SFSpeechRecognizer.

Quick Start

Grant microphone and speech recognition permission, then initialize a SpeechRecognizer (or SpeechAnalyzer on iOS 26+) and start feeding audio to receive transcripts.

Frequently Asked Questions about speech-recognition

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe live microphone audio to text in an iOS app?▼

To transcribe live microphone audio to text, you feed real-time input from AVAudioEngine into Apple's Speech framework. This Skill handles the necessary audio session configuration and microphone permissions to produce real-time transcripts.

What permissions do I need for speech recognition on iOS?▼

Speech recognition on iOS requires explicit microphone and speech recognition authorization prompts. This Skill manages the required permission flows so your app can securely request and receive audio input for transcription.

Can I use SpeechAnalyzer instead of SFSpeechRecognizer for transcription?▼

Yes, you can use SpeechAnalyzer for modern async/await transcription workflows on iOS 26+. For earlier iOS versions, this Skill automatically falls back to the standard SFSpeechRecognizer API.

Does iOS speech recognition support transcribing pre-recorded audio files?▼

Yes, iOS speech recognition supports transcribing pre-recorded audio files. This Skill processes offline or server-based audio file recognition, converting existing audio recordings into searchable, accessible text transcripts.

What is the difference between on-device and server-based speech recognition in iOS?▼

On-device speech recognition processes audio locally without network dependencies, while server-based recognition uses Apple's servers for potentially higher accuracy. This Skill handles both options to suit offline and connected transcription needs.

Do I need optional assets for SpeechAnalyzer on iOS 26+?▼

Yes, using the SpeechAnalyzer API on iOS 26+ requires optional asset support. This Skill incorporates the necessary asset management to enable the modern async/await transcription workflow.

Related Skills

Explore More Software Engineering Skills→
Roy-wonjiRoy-wonji

speech-recognition

Transcribe live microphone and local file speech using Apple's Speech framework.

Community
Intermediate
Prathviraj-jadhavPrathviraj-jadhav

ASR

Transcribe spoken audio from files or streams into structured text.

Community
Intermediate
melissa-pereira-deelmelissa-pereira-deel

Real-Time Audio Engineering

Build glitch-free real-time audio pipelines with AVAudioEngine and Core Audio.

Community
Advanced
anicca-labsanicca-labs

speech-recognition

Facilitate on-device voice-to-text dictation on iOS and Android using expo-speech-recognition.

Official
Intermediate