diff --git a/pytube/captions.py b/pytube/captions.py
index fe84bec3f..544f96ed9 100644
--- a/pytube/captions.py
+++ b/pytube/captions.py
@@ -83,14 +83,15 @@ def xml_caption_to_srt(self, xml_captions: str) -> str:
         """
         segments = []
         root = ElementTree.fromstring(xml_captions)
-        for i, child in enumerate(list(root)):
+        body = root.find("body")
+        for i, child in enumerate(list(body)):
             text = child.text or ""
             caption = unescape(text.replace("\n", " ").replace("  ", " "),)
             try:
-                duration = float(child.attrib["dur"])
+                duration = float(child.attrib["d"])/1000
             except KeyError:
                 duration = 0.0
-            start = float(child.attrib["start"])
+            start = float(child.attrib["t"])/1000
             end = start + duration
             sequence_number = i + 1  # convert from 0-indexed to 1.
             line = "{seq}\n{start} --> {end}\n{text}\n".format(