Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.
-
Updated
Oct 1, 2026 - TypeScript
Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.
A desktop application that estimates where the user is looking on the selected display and renders a red gaze marker at the estimated hit position. MediaPipe dependency-free.
Real-world context insights SDK for React Native apps, enhancing user experience and engagement with a privacy-first approach
Winning submission to the Cambridge Flywheel Hackathon, 2024
Full-stack AI image generation web application optimized for Apple Silicon. All inference runs natively using Core ML + ANE
🎭 Put your face in any GIF — AI face swapping running 100% locally on your Mac (FaceFusion + CoreML). Web app, desktop app & MCP server.
Know which export format (PyTorch/ONNX/CoreML/TensorRT) actually wins on your machine — one command, real benchmarks. Pre-launch.
Local-first Apple Silicon dictation with offline speech recognition, Live transcription, and privacy-preserving text insertion.
A shelf of old phones turned into a device lab: on-device ML benchmarks, UI tests, and visual regression across real iOS and Android hardware, dispatched from one collector
🎨 ChofyAI Studio · Launcher local de IA creativa. Orquesta 5 herramientas: Qwen3-TTS, whisper.cpp, FaceFusion, AceForge y ComfyUI. Validado en macOS Apple Silicon; soporte experimental Windows + CUDA. Tauri 2 + Rust + React. v0.5.1 operativo (5/5 inferencia real).
An end-to-end toolkit for fine-tuning NVIDIA's Parakeet ASR model on custom vocabulary and deploying to Apple devices via CoreML.
Tap an object in a photo and it disappears. Moebius 0.22B inpainting running fully on-device in React Native, no cloud.
Apple-Silicon transcript editor with Core ML transcription and punchy silence controls.
Local Apple Silicon lab for converting, validating, benchmarking, and chatting with small Hugging Face LLMs through Core ML.
Open-source, fully local speech coaching for macOS with Parakeet and Core ML
Benchmarking YOLOv8s and RT-DETR-L across five inference backends, with a live detection app on top
Local-first macOS utility for background removal and color palette extraction.
To associate your repository with the coreml topic, visit your repo's landing page and select "manage topics."