# mu-hashmi/personaplex-mlx

PersonaPlex on Apple Silicon: an MLX port of NVIDIA’s full-duplex speech-to-speech model with realtime local/web modes and offline WAV inference.

**Commercial license**：Commercial OK — 可商用，通常只需保留著作權聲明/授權條款

**Stars**：68
**Source**：https://github.com/mu-hashmi/personaplex-mlx