diff --git a/README.md b/README.md
index d7825b2..6542df7 100644
--- a/README.md
+++ b/README.md
@@ -13,7 +13,7 @@ Wenjiang Zhou
 
 **[github](https://github.com/TMElyralab/MuseTalk)**    **[huggingface](https://huggingface.co/TMElyralab/MuseTalk)**    **Project(comming soon)**    **Technical report (comming soon)**
 
-We introduce `MuseTalk`, a **real-time high quality** lip-syncing model (30fps+ on an NVIDIA Tesla V100). MuseTalk can be applied with virtual human videos, e.g., generated by [MuseV](https://github.com/TMElyralab/MuseV), as a complete solution.
+We introduce `MuseTalk`, a **real-time high quality** lip-syncing model (30fps+ on an NVIDIA Tesla V100). MuseTalk can be applied with input videos, e.g., generated by [MuseV](https://github.com/TMElyralab/MuseV), as a complete virtual human solution.
 
 # Overview
 `MuseTalk` is a real-time high quality audio-driven lip-syncing model trained in the latent space of `ft-mse-vae`, which