Blaizzy/mlx-vlm

run vision and audio language models on your Mac with MLX

speech-to-text and text-to-speech tools for Apple Silicon
Blaizzy/mlx-audio
fast vision-language model for on-device AI
apple/ml-fastvlm
mlx-examples has code for text, image, audio, and multimodal ML models using the MLX framework
ml-explore/mlx-examples
port of Nvidia Parakeet speech recognition models to Apple Silicon using MLX
senstella/parakeet-mlx
MLX: array framework for machine learning on Apple silicon
ml-explore/mlx
Route audio between Mac apps with a virtual loopback driver
ExistentialAudio/BlackHole
real-time voice chat for mac powered by AI
realtime-ai/mac-echo
Toolkit to fine-tune multimodal VLMs with a simple CLI and Python API, featuring ready-made recipes for Florence-2, PaliGemma 2, and Qwen2.5-VL
roboflow/maestro
Toolkit for fine-tuning and training large language and vision models
InternLM/xtuner
run large language models on any device
mlc-ai/mlc-llm