Get a 'generate-contextual-text' job

{
  "data": {
    "parameters": {
      "asset_id": "mux_asset_123abc",
      "output_steering": {
        "audience": "Video developers",
        "voice": "conversational"
      },
      "variants": [
        {
          "key": "product_led",
          "instructions": "Use a promotional, product-led angle."
        },
        {
          "key": "insight_led",
          "instructions": "Use an educational, insight-led angle."
        }
      ],
      "artifacts": [
        {
          "key": "x_post",
          "channel": "x",
          "max_length": {
            "unit": "characters",
            "value": 280
          }
        },
        {
          "key": "blog_post",
          "max_length": {
            "unit": "words",
            "value": 1200
          },
          "format": "markdown"
        }
      ]
    },
    "resources": {
      "assets": [
        {
          "id": "abc123asset",
          "meta": {
            "title": "My Video",
            "creator_id": "user123",
            "external_id": "ext456"
          },
          "_links": {
            "self": {
              "href": "/video/v1/assets/abc123asset"
            }
          }
        }
      ]
    },
    "outputs": {
      "variants": [
        {
          "key": "insight_led",
          "artifacts": [
            {
              "key": "x_post",
              "content": "The hard part of repurposing video isn't generating more words. It's keeping every piece grounded in the original story."
            },
            {
              "key": "blog_post",
              "content": "# Why video repurposing breaks down after the first draft\n\nMost content workflows treat every deliverable as a separate generation problem. A shared source keeps the whole set grounded."
            }
          ]
        }
      ]
    }
  }
}