skills.rest
DFly7
DFly7COMMUNITY
Explore all skills by this author →
GitHub

speech-recognition

Convert spoken audio to text on iOS using Apple's Speech framework.

Updated Mar 31, 2026
Search Tags:#authorization#transcription#ios#speech-recognition#speech-framework#speech-analyzer
One-click install
npx skills add https://github.com/DFly7/iOS-FastAPI-Supabase-AI --skill speech-recognition-dfly7
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech-recognition
Source: https://github.com/DFly7/iOS-FastAPI-Supabase-AI/tree/main/.agents/skills/speech-recognition
Command: npx skills add https://github.com/DFly7/iOS-FastAPI-Supabase-AI --skill speech-recognition-dfly7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribe spoken audio into text on iOS using Apple's Speech framework, enabling real-time transcription, offline/file-based workflows, and flexible recognition options.

Core Features & Use Cases

  • Real-time transcription via live microphone input using SFSpeechRecognizer or SpeechAnalyzer
  • Transcription of pre-recorded audio files for post-processing
  • On-device vs server-based recognition configuration with proper authorization flows

Quick Start

Use the speech-recognition skill to start capturing live microphone input and obtain text transcripts in your app.

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?▼

Transcribe live microphone audio to text in iOS by capturing audio input and routing it continuously through Apple's Speech framework using SFSpeechRecognizer or SpeechAnalyzer to generate real-time text results.

Can I use Apple's Speech framework for pre-recorded audio file transcription?▼

Pre-recorded audio file transcription is supported by passing the audio file URL directly into the Speech framework recognizer, which processes the file and returns text without requiring live microphone input.

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

On-device speech recognition runs entirely locally on the iOS hardware for offline availability and privacy, while server-based recognition routes audio to Apple servers for higher accuracy and broader language support.

Do I need to handle authorization before starting speech recognition on iOS?▼

Authorization is required for speech recognition on iOS, necessitating explicit user permission requests for microphone access and speech data processing prior to initializing the recognizer.

How does the iOS SpeechAnalyzer compare to SFSpeechRecognizer for transcription?▼

SpeechAnalyzer and SFSpeechRecognizer both provide speech transcription on iOS, with SpeechAnalyzer offering modular usage for advanced configurations, while SFSpeechRecognizer handles standard live and file-based recognition tasks.

Are there limitations when using on-device speech recognition in iOS?▼

On-device speech recognition in iOS requires downloaded language models, consumes significant device processing resources, and may offer lower accuracy compared to server-based recognition for certain audio qualities or languages.

Related Skills

Explore More Software Engineering Skills→
yashpalsince2004yashpalsince2004

speech-recognition

Convert live and pre-recorded audio into text with Apple's Speech framework.

Community
Intermediate
valtterimelkkovaltterimelkko
1

audio-transcription-workflow

Convert audio files into structured markdown transcripts via multi-provider pipeline.

Community
Advanced
tuliopc23tuliopc23

axiom-avfoundation-ref

Configure AVAudioSession and build AVAudioEngine pipelines for iOS audio.

Community
Intermediate
JiayueMeng128JiayueMeng128

openai-whisper

Transcribe and translate audio files locally using the Whisper CLI.

Community
Intermediate