diff --git a/README.md b/README.md
index 6f9e2af..828ace6 100644
--- a/README.md
+++ b/README.md
@@ -17,6 +17,14 @@ A core innovation of VibeVoice is its use of continuous speech tokenizers (Acous
The model can synthesize speech up to **90 minutes** long with up to **4 distinct speakers**, surpassing the typical 1-2 speaker limits of many prior models.
+### 🎵 Demo Example
+Listen to a sample of VibeVoice generating multi-speaker conversational audio:
+
+
+
Try it out via [Demo](https://aka.ms/VibeVoice-Demo).
diff --git a/demo/example/1p_EN2CH.mp3 b/demo/example/1p_EN2CH.mp3
new file mode 100644
index 0000000..bcba182
Binary files /dev/null and b/demo/example/1p_EN2CH.mp3 differ
diff --git a/demo/example/2p_see_u_again.mp3 b/demo/example/2p_see_u_again.mp3
new file mode 100644
index 0000000..1d6f8c2
Binary files /dev/null and b/demo/example/2p_see_u_again.mp3 differ