diff --git a/docarray/documents/video.py b/docarray/documents/video.py
index dd011b796fc..5ced0b01974 100644
--- a/docarray/documents/video.py
+++ b/docarray/documents/video.py
@@ -13,7 +13,7 @@ class Video(BaseDocument):
     """
     Document for handling video.
     The Video Document can contain a VideoUrl (`Video.url`), an Audio Document
-    (`Video.audio`), a VideoTensor (`Video.video_tensor`), an AnyTensor representing
+    (`Video.audio`), a VideoTensor (`Video.tensor`), an AnyTensor representing
     the indices of the video's key frames (`Video.key_frame_indices`) and an
     AnyEmbedding (`Video.embedding`).
 
@@ -29,9 +29,9 @@ class Video(BaseDocument):
         vid = Video(
             url='https://github.com/docarray/docarray/tree/feat-add-video-v2/tests/toydata/mov_bbb.mp4?raw=true'
         )
-        vid.audio.tensor, vid.video_tensor, vid.key_frame_indices = vid.url.load()
+        vid.audio.tensor, vid.tensor, vid.key_frame_indices = vid.url.load()
         model = MyEmbeddingModel()
-        vid.embedding = model(vid.video_tensor)
+        vid.embedding = model(vid.tensor)
 
     You can extend this Document:
 
@@ -50,9 +50,9 @@ class MyVideo(Video):
         video = MyVideo(
             url='https://github.com/docarray/docarray/blob/feat-rewrite-v2/tests/toydata/mov_bbb.mp4?raw=true'
         )
-        video.video_tensor = video.url.load_key_frames()
+        video.tensor = video.url.load_key_frames()
         model = MyEmbeddingModel()
-        video.embedding = model(video.video_tensor)
+        video.embedding = model(video.tensor)
         video.name = Text(text='my first video')
 
     You can use this Document for composition:
@@ -75,11 +75,11 @@ class MultiModalDoc(BaseDocument):
             ),
             text=Text(text='hello world, how are you doing?'),
         )
-        mmdoc.video.video_tensor = mmdoc.video.url.load_key_frames()
+        mmdoc.video.tensor = mmdoc.video.url.load_key_frames()
     """
 
     url: Optional[VideoUrl]
     audio: Optional[Audio] = Audio()
-    video_tensor: Optional[VideoTensor]
+    tensor: Optional[VideoTensor]
     key_frame_indices: Optional[AnyTensor]
     embedding: Optional[AnyEmbedding]
diff --git a/tests/integrations/predefined_document/test_video.py b/tests/integrations/predefined_document/test_video.py
index 85cc451e851..397d3e86c4c 100644
--- a/tests/integrations/predefined_document/test_video.py
+++ b/tests/integrations/predefined_document/test_video.py
@@ -13,8 +13,8 @@
 @pytest.mark.parametrize('file_url', [LOCAL_VIDEO_FILE, REMOTE_VIDEO_FILE])
 def test_video(file_url):
     vid = Video(url=file_url)
-    vid.audio.tensor, vid.video_tensor, vid.key_frame_indices = vid.url.load()
+    vid.audio.tensor, vid.tensor, vid.key_frame_indices = vid.url.load()
 
     assert isinstance(vid.audio.tensor, AudioNdArray)
-    assert isinstance(vid.video_tensor, VideoNdArray)
+    assert isinstance(vid.tensor, VideoNdArray)
     assert isinstance(vid.key_frame_indices, NdArray)