diff --git a/README.md b/README.md
index 26228f9..4e68c71 100644
--- a/README.md
+++ b/README.md
@@ -314,6 +314,10 @@ tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen.
    during inference; the default is `False`, and setting it to `True` enables
    randomness:
 
+> [!NOTE]
+> Enabling random sampling will reduce the voice cloning fidelity of the speech
+> synthesis.
+
 ```python
 from indextts.infer_v2 import IndexTTS2
 tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", use_fp16=False, use_cuda_kernel=False, use_deepspeed=False)
diff --git a/docs/README_zh.md b/docs/README_zh.md
index 8af79bc..3b8a205 100644
--- a/docs/README_zh.md
+++ b/docs/README_zh.md
@@ -261,9 +261,9 @@ tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen.
 ```
 
 4. 可直接指定8维情感向量 `[高兴, 愤怒, 悲伤, 害怕, 厌恶, 忧郁, 惊讶, 平静]`，可用`use_random`开启随机情感采样（默认False）：
+
 > [!NOTE]
 > 开启随机采样会降低音色的还原度。
-> 
 
 ```python
 from indextts.infer_v2 import IndexTTS2