diff --git a/docs/source/inference.md b/docs/source/inference.md
index b40445ae..611a2445 100644
--- a/docs/source/inference.md
+++ b/docs/source/inference.md
@@ -124,7 +124,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 print(TTS().list_models())
 
 # Init TTS
-tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1").to(device)
+tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)
 
 # Run TTS
 # ❗ Since this model is multi-lingual voice cloning model, we must set the target speaker_wav and language
@@ -231,4 +231,4 @@ api.tts_with_vc_to_file(
     speaker_wav="target/speaker.wav",
     file_path="ouptut.wav"
 )
-```
\ No newline at end of file
+```