skills.rest
moasq
moasqCOMMUNITY
Explore all skills by this author →
𝕏@foundmodGitHub

speech

Convert live audio streams and pre-recorded files into text.

32|10|Updated Feb 21, 2026
Search Tags:#permissions#speech recognition#voice input#SFSpeechRecognizer#AVAudioEngine
One-click install
npx skills add https://github.com/moasq/nanowave --skill speech-moasq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speech
Source: https://github.com/moasq/nanowave/tree/main/internal/orchestration/skills/features/speech
Command: npx skills add https://github.com/moasq/nanowave --skill speech-moasq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill allows applications to understand and process spoken language, enabling hands-free interaction and voice-controlled features.

Core Features & Use Cases

  • Speech Recognition: Convert spoken audio into text.
  • Live Recognition: Process audio streams in real-time from a microphone.
  • File-Based Recognition: Transcribe audio from existing files.
  • On-Device Recognition: Perform recognition locally for enhanced privacy and offline use.
  • Use Case: Integrate voice commands into your app, allowing users to navigate or control features using their voice.

Quick Start

Use the speech skill to request microphone and speech recognition permissions from the user.

Frequently Asked Questions about speech

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

FAQPage Schema
How do I implement speech recognition in my iOS app using SFSpeechRecognizer?▼

Speech recognition with SFSpeechRecognizer requires requesting specific user permissions and configuring the audio session. This Skill manages that setup, enabling on-device or server-based transcription for live streams and pre-recorded files.

Can I transcribe audio from a pre-recorded file instead of a live microphone stream?▼

Yes, speech recognition can be performed on pre-recorded audio files. The Skill facilitates both file-based transcription and live audio stream processing, allowing you to convert spoken audio into text for various interaction scenarios.

Does SFSpeechRecognizer support on-device speech recognition for offline use?▼

Yes, on-device speech recognition is supported for offline use and enhanced privacy. The Skill configures SFSpeechRecognizer to perform transcription locally, allowing voice-controlled features to function without a network connection.

What permissions do I need to request for live voice input and transcription?▼

Live voice input requires both microphone and speech recognition permissions from the user. This Skill handles requesting these authorizations, which are necessary before capturing audio streams with AVAudioEngine and processing them.

How do I process real-time audio streams for live speech recognition?▼

Processing real-time audio streams requires configuring AVAudioEngine alongside SFSpeechRecognizer. This Skill manages the audio engine setup and recognizer configuration, enabling continuous live recognition as users speak.

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
reedmayhew18reedmayhew18
23

oc-voice

Transcribe voice chat messages with Whisper and route text downstream.

Community
Intermediate
zjunlpzjunlp
1.1k

webshop-query-interpreter

Convert natural language shopping queries into structured product search parameters.

Official
Intermediate
yashpalsince2004yashpalsince2004

speech-recognition

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

Community
Intermediate