join_clips

Concatenate 2-20 images or clips, in the order given, into a single MP4 in the library. A single clip is accepted too when it carries a music bed or narration — that is how a voice-over is laid on one clip. This is how a run of shots becomes one file: generate each clip, carry the last frame into the next with extract_video_frame, then join them here. Images hold for image_duration_seconds (three seconds by default). Every clip keeps its own audio; a music bed is looped to the cut's length and ducked under any voice-over, and each narration line is laid at the second you name. Costs no credits. The cut may not run past 10 minutes, and one account joins one set at a time.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "join_clips",
    "arguments": {
      "sources": [
        {
          "type": "upload",
          "upload_id": "00000000-0000-4000-8000-000000000000"
        }
      ]
    }
  }
}

{
  "type": "object",
  "properties": {
    "sources": {
      "type": "array",
      "items": {
        "anyOf": [
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "upload"
              },
              "upload_id": {
                "type": "string",
                "format": "uuid"
              }
            },
            "required": [
              "type",
              "upload_id"
            ],
            "additionalProperties": false
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "generation"
              },
              "generation_id": {
                "type": "string",
                "format": "uuid"
              }
            },
            "required": [
              "type",
              "generation_id"
            ],
            "additionalProperties": false
          }
        ]
      },
      "minItems": 1,
      "maxItems": 20
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9"
      ]
    },
    "image_duration_seconds": {
      "type": "number",
      "minimum": 0.2,
      "maximum": 600,
      "default": 3
    },
    "music": {
      "type": "object",
      "properties": {
        "source": {
          "$ref": "#/properties/sources/items"
        },
        "gain_db": {
          "type": "integer",
          "minimum": -40,
          "maximum": 0
        }
      },
      "required": [
        "source"
      ],
      "additionalProperties": false
    },
    "narration": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "source": {
            "$ref": "#/properties/sources/items"
          },
          "start_seconds": {
            "type": "number",
            "minimum": 0
          },
          "duration_seconds": {
            "type": "number",
            "exclusiveMinimum": 0
          }
        },
        "required": [
          "source",
          "start_seconds"
        ],
        "additionalProperties": false
      },
      "maxItems": 20
    }
  },
  "required": [
    "sources"
  ],
  "additionalProperties": false
}