group text

meetus/workflow.py

@@ -236,12 +236,25 @@ class ProcessingWorkflow:
         logger.info("Step 2: Running vision analysis on extracted frames...")
         logger.info(f"Loading vision model {self.config.vision_model} to GPU...")
 
+        # Load audio segments for context if transcript exists
+        audio_segments = []
+        transcript_path = self.config.transcript_path or self._get_cached_transcript()
+
+        if transcript_path:
+            transcript_file = Path(transcript_path)
+            if transcript_file.exists():
+                logger.info("Loading audio transcript for context...")
+                merger = TranscriptMerger()
+                audio_segments = merger.load_whisper_transcript(str(transcript_file))
+                logger.info(f"✓ Loaded {len(audio_segments)} audio segments for context")
+
         try:
             vision = VisionProcessor(model=self.config.vision_model)
             screen_segments = vision.process_frames(
                 frames_info,
                 context=self.config.vision_context,
-                deduplicate=not self.config.no_deduplicate
+                deduplicate=not self.config.no_deduplicate,
+                audio_segments=audio_segments
             )
             logger.info(f"✓ Analyzed {len(screen_segments)} frames with vision model")
 
@@ -253,6 +266,11 @@ class ProcessingWorkflow:
             logger.error(f"{e}")
             raise
 
+    def _get_cached_transcript(self) -> Optional[str]:
+        """Get cached Whisper transcript if available."""
+        cached = self.cache_mgr.get_whisper_cache()
+        return str(cached) if cached else None
+
     def _run_ocr_analysis(self, frames_info):
         """Run OCR analysis on frames."""
         logger.info("Step 2: Running OCR on extracted frames...")
@@ -289,7 +307,8 @@ class ProcessingWorkflow:
                 logger.warning(f"Transcript not found: {transcript_path}")
                 logger.info("Proceeding with screen content only...")
             else:
-                audio_segments = merger.load_whisper_transcript(str(transcript_file))
+                # Group audio into 30-second intervals for cleaner reference timestamps
+                audio_segments = merger.load_whisper_transcript(str(transcript_file), group_interval=30)
                 logger.info(f"✓ Loaded {len(audio_segments)} audio segments")
         else:
             logger.info("No transcript provided, using screen content only...")