diff --git a/README.md b/README.md
index a3a266b..ffe8c35 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,7 @@
 [![Technical Report](https://img.shields.io/badge/Technical-Report-red?logo=adobeacrobatreader)](https://arxiv.org/pdf/2508.19205)
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/VibeVoice_colab.ipynb)
 [![Live Playground](https://img.shields.io/badge/Live-Playground-green?logo=gradio)](https://aka.ms/VibeVoice-Demo)
+[![Colab](https://img.shields.io/badge/Run-Colab-orange?logo=googlecolab)](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/VibeVoice_colab.ipynb)
 
 </div>
 <!-- <div align="center">
@@ -31,7 +32,7 @@ The model can synthesize speech up to **90 minutes** long with up to **4 distinc
 ### 🔥 News
 
 - **[2025-08-26] 🎉 We Open Source the [VibeVoice-7B-Preview](https://huggingface.co/WestZhang/VibeVoice-Large-pt) model weights!**
-- **[2025-08-28] 🎉 We add the [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/VibeVoice_colab.ipynb) script for easily use the model.**
+- **[2025-08-28] 🎉 We provide a [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/VibeVoice_colab.ipynb) script for easy access to our model. Due to GPU memory limitations, only VibeVoice-1.5B is supported.**
 
 ### 📋 TODO