Visible Light Communication (VLC) system, a wireless system that utilizing the visible light spectrum to transmit data has been considered to become a complementary technology to radio frequency (RF) wireless technology in overcoming spectrum limitations. Recently, numerous VLC research projects have been conducted. However, many of these experiments were performed under ideal conditions, and only a few demonstrated real-time results with networking capabilities. To address this limitation, this paper proposes and details the design of a real-time VLC prototype that supports TCP/IP networking. First, we propose a system-on-chip (SoC) architecture for a VLC system. We design Register-Transfer-Level (RTL) modules using orthogonal frequency-division multiplexing (OFDM) for time synchronization, channel estimation, and equalization. Additionally, we optimize the Sampling Frequency Offset (SFO) estimation and compensation in the receiver to address the mismatch between TX and RX clock oscillators. The optimization of the SFO module is done by eliminating division operations. To realize full-stack design we integrate our design, consisting baseband processor in an FPGA as physical layer device, Linux’s kernel TCP/IP stack and the analog output to the VLC analog front-end. This full system design are evaluated over real channel at 1 m distance of transmitter and receiver. Experimental evaluations show that our VLC system can do network tests in an end-to-end system with commercial-off-the-shelf (COTS) networking devices and real applications such as internet browsers. Our VLC system offers a maximum real-time net TCP data rate of 6.65 Mb/s as measured using the iperf tool. Theses experimental results show that our VLC system achieves a $6\times $ data rate improvement as compared to the state-of-the-art work. Specifically, our SFO compensator results demonstrate an improvement in TCP data rate of $8.25\times $ and a reduction in frame loss of 22.42%. Moreover, our system also provides design features in terms of flexibility and scalability for future development.