diff --git a/setup.cfg b/setup.cfg
index 4749e2c2a9..7134012af8 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -134,6 +134,7 @@ all =
     ormsgpack  # For Fish Speech
     cachetools  # For Fish Speech
     silero-vad  # For Fish Speech
+    vector-quantize-pytorch<=1.17.3,>=1.14.24 # For Fish Speech
     torchdiffeq  # For F5-TTS
     x_transformers>=1.31.14  # For F5-TTS
     pypinyin  # For F5-TTS
@@ -228,6 +229,7 @@ audio =
     ormsgpack  # For Fish Speech
     cachetools  # For Fish Speech
     silero-vad  # For Fish Speech
+    vector-quantize-pytorch<=1.17.3,>=1.14.24 # For Fish Speech
     torchdiffeq  # For F5-TTS
     x_transformers>=1.31.14  # For F5-TTS
     pypinyin  # For F5-TTS
diff --git a/xinference/deploy/docker/requirements.txt b/xinference/deploy/docker/requirements.txt
index fed496ae6e..4e098fef05 100644
--- a/xinference/deploy/docker/requirements.txt
+++ b/xinference/deploy/docker/requirements.txt
@@ -74,6 +74,7 @@ loralib  # For Fish Speech
 ormsgpack  # For Fish Speech
 cachetools  # For Fish Speech
 silero-vad  # For Fish Speech
+vector-quantize-pytorch<=1.17.3,>=1.14.24 # For Fish Speech
 torchdiffeq  # For F5-TTS
 x_transformers>=1.31.14  # For F5-TTS
 pypinyin  # For F5-TTS
diff --git a/xinference/deploy/docker/requirements_cpu.txt b/xinference/deploy/docker/requirements_cpu.txt
index 8931a2575c..5465e7e1da 100644
--- a/xinference/deploy/docker/requirements_cpu.txt
+++ b/xinference/deploy/docker/requirements_cpu.txt
@@ -69,6 +69,7 @@ loralib  # For Fish Speech
 ormsgpack  # For Fish Speech
 cachetools  # For Fish Speech
 silero-vad  # For Fish Speech
+vector-quantize-pytorch<=1.17.3,>=1.14.24 # For Fish Speech
 torchdiffeq  # For F5-TTS
 x_transformers>=1.31.14  # For F5-TTS
 pypinyin  # For F5-TTS