{
  "output_dir": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014",
  "source": {
    "url": "https://static.wecommunify.com/media/v/3/1618797654/152014.mp4",
    "platform": "static",
    "video_id": "152014"
  },
  "media": {
    "duration_sec": 31.383,
    "width": 682,
    "height": 2308,
    "fps": 60.0,
    "video_codec": "h264",
    "has_audio": true,
    "size_bytes": 10225480
  },
  "llm": {
    "provider": "http",
    "model": "qwen/qwen3-vl-8b",
    "frames_analyzed": 31
  },
  "static_text": [
    {
      "text": "Add sound",
      "first_seen_sec": 0.0,
      "last_seen_sec": 30.0,
      "frame_count": 31
    },
    {
      "text": "Text",
      "first_seen_sec": 0.0,
      "last_seen_sec": 30.0,
      "frame_count": 31
    },
    {
      "text": "Effects",
      "first_seen_sec": 0.0,
      "last_seen_sec": 30.0,
      "frame_count": 31
    },
    {
      "text": "M",
      "first_seen_sec": 0.0,
      "last_seen_sec": 30.0,
      "frame_count": 31
    }
  ],
  "description": "The video shows a man recording himself in a selfie-style format while editing it in a social media app, with the editing interface constantly visible at the bottom. He wears a green hoodie over a white t-shirt and frequently gestures, speaks, or smiles directly to the camera, often pointing or raising his hands for emphasis. The on-screen text—“Add sound / Sound / Text / Effects / M”—remains static throughout, indicating the video is being edited and not yet published. The setting appears to be indoors, likely a living room, with ceiling fans and wall decor in the background. The man’s expressions and movements suggest he’s engaging with his audience, possibly narrating or reacting to something, with the editing tools serving as a visual reminder of the video’s behind-the-scenes creation.",
  "frames": [
    {
      "index": 0,
      "timestamp_sec": 0.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00001.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with his eyes closed and smiling is shown in a close-up shot within a video editing interface. The interface displays a timeline at 0:00, with options to add sound, text, and effects visible at the bottom. The video appears to be a short-form social media clip."
    },
    {
      "index": 1,
      "timestamp_sec": 1.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00002.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a nose ring and ear piercing, wearing a white t-shirt and green zip-up hoodie, smiles at the camera in a selfie-style video. The video editing interface is visible, showing a timeline at 00:02, with options for sound, text, and effects."
    },
    {
      "index": 2,
      "timestamp_sec": 2.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00003.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a nose ring and earrings, wearing a white t-shirt and green zip-up hoodie, looks off to the side with a surprised or amused expression. The video is being edited in a social media app, with a timeline showing 2.0 seconds elapsed, and editing options like 'Add sound', 'Text', and 'Effects' visible at the bottom."
    },
    {
      "index": 3,
      "timestamp_sec": 3.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00004.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is filming a short-form social video, pointing at the camera with a surprised or emphatic expression. The video editing interface is visible, showing a timeline with the playhead at 3.0 seconds, and options for sound, text, and effects at the bottom."
    },
    {
      "index": 4,
      "timestamp_sec": 4.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00005.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is filming a short-form social video, looking directly at the camera with his mouth open as if speaking or singing. The video editing interface is visible below, showing a timeline at 4.0 seconds, with options to add sound, text, and effects."
    },
    {
      "index": 5,
      "timestamp_sec": 5.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00006.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a white t-shirt and green hoodie is shown in a selfie-style video frame, looking upward with his mouth open. The video editing interface is visible below, showing a timeline with a playhead at 00:06, and options for sound, text, and effects."
    },
    {
      "index": 6,
      "timestamp_sec": 6.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00007.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a nose ring and ear studs, wearing a white t-shirt and green zip-up hoodie, smiles at the camera in a selfie-style video. The video editing interface is visible, showing a timeline at 6.0 seconds, with options to add sound, text, and effects."
    },
    {
      "index": 7,
      "timestamp_sec": 7.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00008.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a close-up shot, speaking directly to the camera in what appears to be a video editing interface. The video timeline at the bottom indicates the current frame is at 7.0 seconds. The interface displays options to add sound, text, and effects, suggesting this is a social media video being edited."
    },
    {
      "index": 8,
      "timestamp_sec": 8.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00009.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a selfie-style video frame, wearing a white t-shirt and green zip-up hoodie, speaking or reacting to the camera. The video editing interface is visible, showing a timeline at 8.0 seconds, with options to add sound, text, and effects."
    },
    {
      "index": 9,
      "timestamp_sec": 9.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00010.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a close-up shot, appearing to be recording or editing a short-form social video. He is wearing a white t-shirt and a green zip-up hoodie. The video editing interface is visible, with a timeline showing the current frame at 00:08, and options for adding sound, text, and effects. The setting appears to be indoors, with a ceiling fan and decorative wall elements visible in the background."
    },
    {
      "index": 10,
      "timestamp_sec": 10.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00011.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a close-up shot, singing or speaking with his mouth open and gesturing with his hand. The video is being edited in a social media app, with a timeline at 10.0 seconds, and editing options like 'Add sound', 'Text', and 'Effects' visible at the bottom."
    },
    {
      "index": 11,
      "timestamp_sec": 11.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00012.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a close-up shot, wearing a white t-shirt and green hoodie, gesturing with his right hand. The video is being edited in a social media app, with a timeline at 11.0 seconds, and editing tools like 'Add sound', 'Sound', 'Text', 'Effects', and 'M' visible at the bottom."
    },
    {
      "index": 12,
      "timestamp_sec": 12.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00013.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a nose ring and ear piercings, wearing a white t-shirt and green zip-up hoodie, is filming a short-form video. He is looking at the camera with his mouth open and his right hand raised in front of his face. The video editing interface is visible, showing a timeline at 00:12, with options to add sound, text, and effects."
    },
    {
      "index": 13,
      "timestamp_sec": 13.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00014.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with braided hair, wearing a white t-shirt and green zip-up hoodie, looks directly at the camera in a selfie-style video. The video editing interface is visible, showing a timeline with the current frame at 00:14, and options for sound, text, and effects at the bottom."
    },
    {
      "index": 14,
      "timestamp_sec": 14.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00015.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a close-up shot, pointing his finger directly at the camera while speaking. The video is being edited in a social media app, with a timeline at 14.0 seconds, and editing options like 'Add sound', 'Text', and 'Effects' visible at the bottom of the screen."
    },
    {
      "index": 15,
      "timestamp_sec": 15.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00016.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a selfie-style video frame, wearing a white t-shirt and green vest, gesturing with his right hand. The video editing interface is visible, showing a timeline with the playhead at 00:16, and options for sound, text, and effects at the bottom."
    },
    {
      "index": 16,
      "timestamp_sec": 16.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00017.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with his eyes closed and mouth slightly open is shown in a close-up shot, appearing to be singing or speaking. He is wearing a white t-shirt under a green hoodie. The video is being edited in a social media app, with a timeline visible below showing the current position at 00:16 of a 31.4s clip. UI elements for adding sound, text, and effects are displayed at the bottom."
    },
    {
      "index": 17,
      "timestamp_sec": 17.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00018.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with his mouth open and hands raised is shown in a video editing interface at 17.0 seconds. The video player displays a timeline with the current time at 00:18, and editing options like 'Add sound', 'Sound', 'Text', 'Effects', and 'M' are visible at the bottom."
    },
    {
      "index": 18,
      "timestamp_sec": 18.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00019.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a green hoodie and white t-shirt is singing or speaking enthusiastically in a selfie-style video. The video editing interface is visible, showing a timeline at 00:18, with options to add sound, text, and effects. The setting appears to be indoors, with a ceiling fan and decorative wall elements in the background."
    },
    {
      "index": 19,
      "timestamp_sec": 19.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00020.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a nose ring and ear piercing, wearing a green zip-up hoodie over a white t-shirt, smiles and speaks directly to the camera in a selfie-style video. The video editing interface is visible, showing a timeline at 00:18, with options to add sound, text, and effects."
    },
    {
      "index": 20,
      "timestamp_sec": 20.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00021.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with a nose ring and short hair, wearing a green hoodie over a white t-shirt, is shown in a close-up shot. He is gesturing with his right hand while speaking, with a ceiling fan and decorative wall elements visible in the background. The video editing interface is overlaid, showing a timeline at 20.0 seconds, a pause button, and options for sound, text, and effects."
    },
    {
      "index": 21,
      "timestamp_sec": 21.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00022.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is speaking directly to the camera in a video editing interface. The video is paused at 22 seconds, with a timeline and editing tools visible below the frame, including options to add sound, text, and effects."
    },
    {
      "index": 22,
      "timestamp_sec": 22.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00023.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a close-up shot, speaking and gesturing with his hands in what appears to be a video editing interface. The video is paused at the 22-second mark, with a timeline and editing controls visible below the frame. The interface includes options to add sound, text, and effects."
    },
    {
      "index": 23,
      "timestamp_sec": 23.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00024.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with short hair and a beard, wearing a green hoodie over a white t-shirt, is centered in the frame. He is gesturing with both hands, pointing his index fingers toward the camera. The video is being edited in a social media app, with a timeline at the bottom showing the current playback position at 00:24, and editing options like 'Add sound', 'Sound', 'Text', 'Effects', and 'M' visible."
    },
    {
      "index": 24,
      "timestamp_sec": 24.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00025.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is centered in the frame, looking at the camera with a slight smile. The video editing interface is visible, showing a timeline at 00:24, with options to add sound, text, and effects. The setting appears to be indoors, with a ceiling fan and wall decor visible in the background."
    },
    {
      "index": 25,
      "timestamp_sec": 25.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00026.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man with his eyes closed is shown in a close-up shot, wearing a green zip-up hoodie over a white t-shirt. The video is being edited in a social media app, with a timeline at 25.0 seconds, and editing options like 'Add sound', 'Text', and 'Effects' visible at the bottom."
    },
    {
      "index": 26,
      "timestamp_sec": 26.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00027.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is shown in a selfie-style video frame, looking at the camera. The video editing interface is visible, showing a timeline with the current frame at 00:26 of a 31.4s clip, and options for sound, text, and effects at the bottom."
    },
    {
      "index": 27,
      "timestamp_sec": 27.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00028.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man is shown in a selfie-style video frame, wearing a green hoodie over a white t-shirt, in what appears to be a living room. The video editing interface is visible at the bottom, with a timeline indicating 27 seconds into a 31.4-second clip, and options for sound, text, and effects."
    },
    {
      "index": 28,
      "timestamp_sec": 28.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00029.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is shown in a selfie-style video frame, smiling and looking at the camera. The video editing interface is visible below, showing a timeline at 00:28 of a 00:30 clip, with an 'Add sound' button and editing options like Sound, Text, and Effects."
    },
    {
      "index": 29,
      "timestamp_sec": 29.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00030.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man in a green hoodie and white t-shirt is shown in a selfie-style video frame, with a video editing interface overlayed. The interface displays a timeline with the current time at 00:28, a pause button, and options to add sound, text, and effects. The video appears to be in editing mode on a mobile app."
    },
    {
      "index": 30,
      "timestamp_sec": 30.0,
      "path": "/Users/artem/PycharmProjects/socialNetworkVideoAnalyzer/out_wecommunify/152014/frames/frame_00031.jpg",
      "on_screen_text": [
        "Add sound",
        "Text",
        "Effects",
        "M"
      ],
      "description": "A man wearing a green hoodie over a white t-shirt is shown in a selfie-style video frame, smiling and looking at the camera. The video editing interface is visible below, showing a timeline at 00:30, with options for sound, text, and effects."
    }
  ],
  "timings_sec": {
    "llm_frames": 135.28,
    "llm_summary": 10.84
  }
}