3D style transfer aims to generate novel, stylized views while maintaining multi-view consistency. However, current approaches primarily focus on uniformly stylizing entire 3D scenes, limiting the versatility of 3D style transfer. To address this limitation, we propose Text Guided Zero-Shot 3D Style Transfer of Neural Radiance Fields (TGStyleRF), which incorporates the language radiance field into the 3D style transfer based on NeRF, enabling flexible stylization guided by text queries. By the language modeling of the 3D neural radiance field, the spatial position can be bounded with dense semantics, so as to stylize the 3D scene selectively through text-guided. Furthermore, our method leverages both low-level texture and high-level semantics to enhance localization quality. Experimental results demonstrate that, with the integration of the language model and Cross-Feature-Localization (CFL), TGStyleRF achieves greater flexibility and precision in stylization.