{
  "name": "Narrating over a video using multimodal AI",
  "nodes": [
    {
      "id": "6d16b5be-8f7b-49f2-8523-9b84c62f2759",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1960,
        660
      ]
    },
    {
      "id": "a6084f09-9a4f-478a-ac1a-ab1413628c1f",
      "name": "Capture Frames",
      "type": "n8n-nodes-base.code",
      "position": [
        720,
        460
      ]
    },
    {
      "id": "b45e82a4-f304-4733-a9cf-07cae6df13ea",
      "name": "Split Out Frames",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        920,
        460
      ]
    },
    {
      "id": "83d29c51-a415-476d-b380-1ca5f0d4f521",
      "name": "Download Video",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        329,
        346
      ]
    },
    {
      "id": "0304ebb5-945d-4b0b-9597-f83ae8c1fe31",
      "name": "Convert to Binary",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        1480,
        500
      ]
    },
    {
      "id": "32a21e1d-1d8b-411e-8281-8d0e68a06889",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        149,
        346
      ]
    },
    {
      "id": "0ad2ea6a-e1f4-4b26-a4de-9103ecbb3831",
      "name": "Combine Script",
      "type": "n8n-nodes-base.aggregate",
      "position": [
        2640,
        360
      ]
    },
    {
      "id": "2d9bb91a-3369-4268-882f-f97e73897bb8",
      "name": "Upload to GDrive",
      "type": "n8n-nodes-base.googleDrive",
      "position": [
        3040,
        360
      ]
    },
    {
      "id": "137185f6-ba32-4c68-844f-f50c7a5a261d",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -440,
        0
      ],
      "parameters": {
        "width": 476.34074202271484,
        "height": 586.0597334122469,
        "content": "## Try It Out!\n\n### This n8n template takes a video and extracts frames from it which are used with a multimodal LLM to generate a script. The script is then passed to the same multimodal LLM to gener"
      }
    },
    {
      "id": "23700b04-2549-4121-b442-4b92adf7f6d6",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        60,
        120
      ],
      "parameters": {
        "width": 459.41860465116287,
        "height": 463.313953488372,
        "content": "## 1. Download Video\n[Learn more about the HTTP Request node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.httprequest/)\n\nIn this demonstration, we'll download a stock video from"
      }
    },
    {
      "id": "0a42aeb0-96cd-401c-abeb-c50e0f04f7ad",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        560,
        120
      ],
      "parameters": {
        "width": 605.2674418604653,
        "height": 522.6860465116279,
        "content": "## 2. Split Video into Frames\n[Learn more about the Code node](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.code/)\n\nWe need to think of videos are a sum of 2 parts; a visual trac"
      }
    },
    {
      "id": "b518461c-13f1-45ae-a156-20ae6051fc19",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        560,
        660
      ],
      "parameters": {
        "width": 418.11627906976724,
        "height": 132.89534883720933,
        "content": "### 🚨 PERFORMANCE WARNING!\nUsing large videos or capturing a large number of frames is really memory intensive and could crash your n8n instance. Be sure you have sufficient memory and to optimise the"
      }
    },
    {
      "id": "585f7a7f-1676-4bc3-a6fb-eace443aa5da",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1200,
        118.69767441860472
      ],
      "parameters": {
        "width": 1264.8139534883715,
        "height": 774.3720930232558,
        "content": "## 3. Use Vision AI to Narrate on Batches of Frames\n[Read more about the Basic LLM node](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n\nTo keep withi"
      }
    },
    {
      "id": "42c002a3-37f6-4dd7-af14-20391b19cb5a",
      "name": "Stay Within Service Limits",
      "type": "n8n-nodes-base.wait",
      "position": [
        2280,
        640
      ]
    },
    {
      "id": "5beb17fa-8a57-4c72-9c3b-b7fdf41b545a",
      "name": "For Every 15 Frames",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        1320,
        380
      ]
    },
    {
      "id": "9a57256a-076a-4823-8cad-3b64a17ff705",
      "name": "Resize Frame",
      "type": "n8n-nodes-base.editImage",
      "position": [
        1640,
        500
      ]
    },
    {
      "id": "3e776939-1a25-4ea0-8106-c3072d108106",
      "name": "Aggregate Frames",
      "type": "n8n-nodes-base.aggregate",
      "position": [
        1800,
        500
      ]
    },
    {
      "id": "3a973a9c-2c7a-43c5-9c45-a14d49b56622",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2500,
        120.6860465116277
      ],
      "parameters": {
        "width": 769.1860465116274,
        "height": 487.83720930232533,
        "content": "## 4. Generate Voice Over Clip Using TTS\n[Read more about the OpenAI node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-langchain.openai)\n\nFinally with our generated script parts, we c"
      }
    },
    {
      "id": "92e07c18-4058-4098-a448-13451bd8a17a",
      "name": "Use Text-to-Speech",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        2840,
        360
      ]
    },
    {
      "id": "0696c336-1814-4ad4-aa5e-b86489a4231e",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        61,
        598
      ],
      "parameters": {
        "width": 458.1279069767452,
        "height": 296.8139534883723,
        "content": "**The video used in this demonstration is**\n© [Coverr-Free-Footage](https://pixabay.com/users/coverr-free-footage-1281706/) via [Pixabay](https://pixabay.com/videos/india-street-busy-rickshaw-peo"
      }
    },
    {
      "id": "81185ac4-c7fd-4921-937f-109662d5dfa5",
      "name": "Generate Narration Script",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1960,
        500
      ]
    }
  ],
  "connections": {
    "Resize Frame": {
      "main": [
        [
          {
            "node": "Aggregate Frames",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Capture Frames": {
      "main": [
        [
          {
            "node": "Split Out Frames",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Combine Script": {
      "main": [
        [
          {
            "node": "Use Text-to-Speech",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Download Video": {
      "main": [
        [
          {
            "node": "Capture Frames",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Aggregate Frames": {
      "main": [
        [
          {
            "node": "Generate Narration Script",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Out Frames": {
      "main": [
        [
          {
            "node": "For Every 15 Frames",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Convert to Binary": {
      "main": [
        [
          {
            "node": "Resize Frame",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Generate Narration Script",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Use Text-to-Speech": {
      "main": [
        [
          {
            "node": "Upload to GDrive",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "For Every 15 Frames": {
      "main": [
        [
          {
            "node": "Combine Script",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Convert to Binary",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate Narration Script": {
      "main": [
        [
          {
            "node": "Stay Within Service Limits",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Stay Within Service Limits": {
      "main": [
        [
          {
            "node": "For Every 15 Frames",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "Download Video",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}