Update app.py

app.py

@@ -203,7 +203,7 @@ async def transcript_to_speech(transcript_text, voice, rate, pitch):
     max_end_time_ms = 0
     previous_end_time_ms = 0
     previous_start_time_ms = 0 # Keep track of the *start* time of the previous segment
-
+    next_start_time_ms = None # Keep track of the *start* time of the next segment
 
     for i, line in enumerate(lines):
         start_time, audio_paths = await process_transcript_line(line, voice, rate, pitch)
@@ -227,6 +227,7 @@ async def transcript_to_speech(transcript_text, voice, rate, pitch):
                     if current_audio_duration > time_difference:
                         intended_start_time = previous_end_time_ms
 
+
                 timed_audio_segments.append({'start': intended_start_time, 'audio': combined_line_audio})
                 previous_start_time_ms = start_time #update previous start time
                 previous_end_time_ms = max(previous_end_time_ms, intended_start_time + current_audio_duration)
@@ -304,3 +305,4 @@ async def create_demo():
 if __name__ == "__main__":
     demo = asyncio.run(create_demo())
     demo.launch()
+