Fish Audio

Shijia Liao graduated from the University of Maryland in 2023 and joined NVIDIA to work on Vision Foundation Model scaling across large GPU clusters. Starting in his teens he contributed to widely adopted open-source voice-synthesis projects including So-VITS-SVC and GPT-SoVITS, accumulating over seven years of experience in voice AI research before founding Fish Audio. He departed NVIDIA to prototype Fish Audio's emotional text-to-speech and high-fidelity voice-cloning platform, combining prosody modeling with semantic cues to achieve real-world voice replication.