🎤 Enhance your voice-to-text transcriptions with WhisperClip, prioritizing privacy and featuring AI improvements for macOS users.
-
Updated
Nov 13, 2025 - Swift
🎤 Enhance your voice-to-text transcriptions with WhisperClip, prioritizing privacy and featuring AI improvements for macOS users.
On-device Speech Recognition for Apple Silicon
EmoAssist is a SwiftUI-based voice therapy companion that listens, understands, and responds empathetically using AI-powered emotion detection and real-time voice synthesis.
Some implemented use cases for SFSpeechRecognizer
Linguora est une application iOS développée en SwiftUI, combinant des capteurs embarqués avec des APIs pour proposer une traduction enrichie.
CDPASR is a lightweight Swift library that simplifies speech recognition by leveraging system-native ASR capabilities. It provides an easy-to-use interface to integrate seamless speech-to-text functionality into your iOS/macOS Swift projects, with minimal setup and full utilization of platform-built-in speech recognition features.
iOS application for finding formants in spoken sounds
Apple AI Research & Demo Applications - Foundation Models, Vision Framework, and Speech-to-Text capabilities
A lightweight macOS menu bar app for quick on-device audio transcription using Parakeet v3 Multilingual. Press a hotkey, record your thoughts, and get instant text that's automatically inserted in your active app.
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
An AI powered productivity assistant to VimKit that helps users complete tasks more efficiently.
🧠 Professional AI/ML framework for Swift. 12 specialized modules, Neural Engine optimized, privacy-first, multi-platform (iOS/macOS/visionOS). Production-ready with comprehensive docs.
Transcriber for MacOS
Privacy-focused local dictation for macOS powered by OpenAI's Whisper
Lightweight on-device keyword spotting engine for iOS using CoreML and real-time audio streaming.
OtosakuStreamingASR-iOS is a real-time speech recognition engine for iOS, built with Swift and Core ML. It uses a fast and lightweight streaming Conformer model optimized for on-device inference. Designed for developers who need efficient audio transcription on mobile.
Attention test based on Stroop Test that take speech as input transcripts it in text and proceeds in the test to evaluate your score.
Takarir is a lightweight, user-friendly macOS app that lets you generate subtitles from video files using advanced speech recognition — fast, offline, and privacy-friendly.
POC using Apple's Speech framework demonstrating real-time speech recognition and transcription for macOS
Add a description, image, and links to the speech-recognition topic page so that developers can more easily learn about it.
To associate your repository with the speech-recognition topic, visit your repo's landing page and select "manage topics."