speech-recognition

Transcribe live microphone input and audio files using Apple's Speech framework.

981|50|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/dpearson2699/swift-ios-skills --skill speech-recognition-dpearson2699
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: speech-recognition
Source: https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/speech-recognition
Command: npx skills add https://github.com/dpearson2699/swift-ios-skills --skill speech-recognition-dpearson2699

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the conversion of spoken language into written text, facilitating accessibility, automation, and data analysis from audio sources.

Core Features & Use Cases

  • Live Transcription: Real-time speech-to-text for voice commands or dictation.
  • Audio File Analysis: Transcribe pre-recorded audio files (e.g., interviews, lectures).
  • On-Device vs. Server Recognition: Choose between offline processing or cloud-based accuracy.
  • Modern API Support: Integrates with the latest SpeechAnalyzer API (iOS 26+) for advanced features.
  • Use Case: Automatically transcribe customer support calls to identify key issues and sentiment.

Quick Start

Use the speech-recognition skill to transcribe the audio from the attached file 'meeting_recording.m4a'.

Frequently Asked Questions about speech-recognition

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

FAQPage Schema
How do I transcribe speech to text from an audio file in iOS?

To transcribe speech to text from an audio file in iOS, you can process pre-recorded audio files like interviews or lectures using Apple's Speech framework to generate written text.

Can I use the Speech framework for live microphone transcription in Swift?

Yes, the Speech framework supports live transcription for real-time speech-to-text, enabling voice commands or dictation directly from microphone input in Swift.

Does iOS speech recognition support on-device offline processing?

Yes, iOS speech recognition supports on-device offline processing, allowing you to choose between local device recognition and server-based cloud recognition for improved accuracy.

What is the best way to handle speech recognition in iOS 26+?

The best way to handle speech recognition in iOS 26+ is using the modern SpeechAnalyzer API, which provides advanced asynchronous processing features for transcribing spoken audio.

Does transcribing audio with the Speech framework require an internet connection?

Transcribing audio does not strictly require an internet connection because the Speech framework offers on-device offline recognition, though server-based recognition needs network access for higher accuracy.