Update app.py

app.py

@@ -73,7 +73,7 @@ class YouTubeDownloader:
             1. Create detailed scene descriptions that include:
                - Physical appearance of people (age, gender, clothing, hair, etc.)
                - Exact actions being performed
-               - Dialogue or speech (if mentioned in title/description)
+               - Dialogue or speech (actual lines spoken, inferred if not explicitly given)
                - Setting and environment details
                - Props, objects, or products being shown
                - Visual effects, text overlays, or graphics
@@ -99,6 +99,10 @@ class YouTubeDownloader:
                - Transitions between scenes
             
             5. Write descriptions as if you're watching the video in real-time, noting everything visible and audible.
+
+            6.Dialogue:
+            - Include short direct speech/dialogue wherever possible.
+            -  If no exact lines are known, intelligently infer short probable phrases (e.g., "Let's get started!", "Here's how you do it.", etc.)
             
             Based on the title and description, intelligently infer what would likely happen in each time segment. Consider the video type and create contextually appropriate, detailed descriptions.
             """