diff --git a/src/media.ts b/src/media.ts
index df21d41..5ecc5aa 100644
--- a/src/media.ts
+++ b/src/media.ts
@@ -143,7 +143,12 @@ export function transformToFlatDirectory(
         } else {
           $(elem).attr('src', url);
         }
-      } else console.log('Referenced file not found: ' + assetReference);
+      } else
+        console.log(
+          `Referenced file not found: ${assetReference} elem=${$(
+            paths[assetReference]
+          ).prop('tagName')}`
+        );
     });
     modified = true;
   });
@@ -579,6 +584,9 @@ function findFromDOM(
   $('video source').each((i: any, elem: any) => {
     paths[$(elem).attr('src')] = [elem, ...$(paths[$(elem).attr('src')])];
   });
+  $('video track').each((i: any, elem: any) => {
+    paths[$(elem).attr('src')] = [elem, ...$(paths[$(elem).attr('src')])];
+  });
 
   $('embed_activity source').each((i: any, elem: any) => {
     paths[$(elem).text()] = [elem, ...$(paths[$(elem).text()])];
diff --git a/src/resources/common.ts b/src/resources/common.ts
index 14a85fe..2a1b5ed 100644
--- a/src/resources/common.ts
+++ b/src/resources/common.ts
@@ -343,6 +343,9 @@ export function standardContentManipulations($: any) {
   DOM.renameAttribute($, 'video source', 'src', 'url');
   DOM.renameAttribute($, 'video', 'type', 'contenttype');
   DOM.renameAttribute($, 'audio', 'type', 'audioType');
+  // video <track> subelement with .vtt subtitle file => torus captions child
+  DOM.rename($, 'video track[kind="subtitles"]', 'captions');
+  DOM.renameAttribute($, 'video captions', 'srclang', 'language_code');
 
   DOM.rename($, 'extra', 'popup');
 
diff --git a/src/utils/xml.ts b/src/utils/xml.ts
index f392a8d..0e70888 100644
--- a/src/utils/xml.ts
+++ b/src/utils/xml.ts
@@ -399,6 +399,17 @@ export function toJSON(
           } else {
             top().src = getAllOfType(top().children, 'source');
           }
+          // video may carry vtt subtitle file(s) in captions children
+          const captions = getAllOfType(top().children, 'captions');
+          if (captions != null && captions.length > 0) {
+            top().captions = captions.map((c: any) => {
+              return {
+                label: c.label,
+                language_code: c.language_code,
+                src: c.src,
+              };
+            });
+          }
 
           top().children = [{ text: ' ' }];
           if (top().width !== undefined) {