diff --git a/doc/source/getting_started/index.rst b/doc/source/getting_started/index.rst
index 521fc22be7..8c8a0c129b 100644
--- a/doc/source/getting_started/index.rst
+++ b/doc/source/getting_started/index.rst
@@ -9,6 +9,7 @@ Getting Started
    :maxdepth: 2
 
    installation
+   installation_npu
    using_xinference
    logging
    using_docker_image
diff --git a/doc/source/models/builtin/audio/fishspeech-1.4.rst b/doc/source/models/builtin/audio/fishspeech-1.4.rst
deleted file mode 100644
index c256495d67..0000000000
--- a/doc/source/models/builtin/audio/fishspeech-1.4.rst
+++ /dev/null
@@ -1,19 +0,0 @@
-.. _models_builtin_fishspeech-1.4:
-
-==============
-FishSpeech-1.4
-==============
-
-- **Model Name:** FishSpeech-1.4
-- **Model Family:** FishAudio
-- **Abilities:** text-to-audio
-- **Multilingual:** True
-
-Specifications
-^^^^^^^^^^^^^^
-
-- **Model ID:** fishaudio/fish-speech-1.4
-
-Execute the following command to launch the model::
-
-   xinference launch --model-name FishSpeech-1.4 --model-type audio
\ No newline at end of file
diff --git a/doc/source/reference/index.rst b/doc/source/reference/index.rst
index c44d629e6e..9209fe6530 100644
--- a/doc/source/reference/index.rst
+++ b/doc/source/reference/index.rst
@@ -87,4 +87,4 @@ VideoModelHandle
 
    xinference.client.handlers.VideoModelHandle
 
-   xinference.client.handlers.ImageModelHandle.text_to_video
+   xinference.client.handlers.VideoModelHandle.text_to_video
diff --git a/xinference/client/handlers.py b/xinference/client/handlers.py
index 48e625c83f..f2e82d9221 100644
--- a/xinference/client/handlers.py
+++ b/xinference/client/handlers.py
@@ -1,6 +1,9 @@
 from .restful.restful_client import (  # noqa: F401
     RESTfulAudioModelHandle as AudioModelHandle,
 )
+from .restful.restful_client import (  # noqa: F401
+    RESTfulVideoModelHandle as VideoModelHandle,
+)
 from .restful.restful_client import (  # noqa: F401
     RESTfulChatModelHandle as ChatModelHandle,
 )