ios-speech-recognition

Configure SFSpeechRecognizer and AVAudioEngine for on-device iOS speech transcription.

Updated Dec 23, 2025
One-click install
npx skills add https://github.com/co-labs-co/context-harness-skills --skill ios-speech-recognition
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ios-speech-recognition
Source: https://github.com/co-labs-co/context-harness-skills/tree/main/skill/ios-speech-recognition
Command: npx skills add https://github.com/co-labs-co/context-harness-skills --skill ios-speech-recognition

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

On-device iOS speech-to-text enables apps to convert spoken words into text without relying on network services, improving privacy and latency.

Core Features & Use Cases

  • Setup SFSpeechRecognizer and AVAudioEngine for real-time transcription in iOS apps.
  • Handle user permissions and microphone access for seamless dictation and voice command workflows.
  • Use cases include dictation, voice commands, accessibility features, and hands-free interactions on iPhone/iPad.

Quick Start

Integrate Apple's Speech Framework into an iOS project, request necessary permissions, and begin capturing audio to transcribe speech.

Frequently Asked Questions about ios-speech-recognition

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

FAQPage Schema
How do I implement on-device speech recognition in an iOS app?

To implement on-device speech recognition in an iOS app, configure SFSpeechRecognizer and AVAudioEngine, request microphone permissions in Info.plist, and manage audio sessions to transcribe spoken words into low-latency text.

Can I use SFSpeechRecognizer for real-time dictation offline?

Yes, SFSpeechRecognizer supports real-time dictation and offline capability for iOS apps. By pairing it with AVAudioEngine, you can achieve low-latency, on-device transcription without relying on network services.

What permissions do I need for AVAudioEngine speech transcription?

For AVAudioEngine speech transcription, you must configure appropriate Info.plist permissions and handle user requests for microphone access. This ensures seamless dictation and voice command workflows while maintaining user privacy.

Why choose on-device iOS speech-to-text over network-based recognition?

On-device iOS speech-to-text is chosen over network-based recognition to improve privacy and reduce latency. It processes spoken words locally on the iPhone or iPad, enabling hands-free interactions without depending on network services.

Does iOS speech recognition work for voice commands and accessibility features?

Yes, iOS speech recognition works for voice commands and accessibility features. By capturing audio locally and transcribing speech into text, it enables hands-free interactions and dictation within mobile apps.

Are there limitations to using SFSpeechRecognizer for continuous transcription?

While SFSpeechRecognizer enables real-time transcription, managing audio sessions and recognition results is required to handle continuous dictation properly, as on-device processing demands careful resource and session management.