UGC Fans

Make ads, images and video from a URL; every paid generation is quoted in credits first

我该使用它吗

质量与安全性

B
描述质量
98%
模式完整度
96%
命名质量
80%
投毒风险
0%
权限匹配度
100%
协议合规性
100%

发现(8)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_finish_clip 中
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_transcribe 中
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_list_files 中
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_make_ad 中
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_make_performance 中
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_read_reference 中
  • MEDIUMTool description contains URL to non-standard domain在 ugcfans_save_asset 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~7,181token 数(工具定义)
~1.9 KB典型响应大小
对注意力有显著影响(占 128k 上下文窗口的 5.61%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "make": {
      "url": "https://mcp.ugc.fans/mcp"
    }
  }
}

远程端点

https://mcp.ugc.fans/mcpstreamable-http

它能做什么

工具清单

工具(26)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢ugcfans_search_templates(query)

Lists the ad templates, ad features and creation modes UGC Fans offers, each with its slug, name and a sentence on what it makes. Free, and needs no sign-in. A template slug goes into ugcfans_make_ad as template; a feature slug as feature.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Words to look for in names and descriptions, such as \"testimonial\" or \"product video\". Leave out to list everything.",
      "maxLength": 200
    }
  },
  "required": [],
  "additionalProperties": false
}
🟢ugcfans_get_account

Shows the signed-in account's credits left, credits granted and spent this period, when they expire, its plan and whether the account is admitted to UGC Fans. Free.

输入模式

{
  "type": "object",
  "properties": {},
  "required": [],
  "additionalProperties": false
}
⚪ugcfans_capture_website(url, viewport)

Opens a public web page in a sandboxed browser, records its text, pictures and layout, and returns a job whose result is a capture id. A capture is the raw material of ugcfans_make_launch_film and ugcfans_make_site_sting. Free of credits. Calling it confirms the person has the right to reuse the page's content in their own films. Only http and https pages on ports 80 and 443 can be captured.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The address of the page, starting with https:// or http://.",
      "maxLength": 2048
    },
    "viewport": {
      "type": "string",
      "description": "desktop captures a 1280 by 900 window (the default); phone captures 390 by 844 at twice the density.",
      "enum": [
        "desktop",
        "phone"
      ]
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢ugcfans_get_capture(capture)

Reads a finished capture: the address it ended on, the parts of the page that can go into a film (node_id, role and the first words), and whether a launch film can be made from it. Free.

输入模式

{
  "type": "object",
  "properties": {
    "capture": {
      "type": "string",
      "description": "The capture id from the finished ugcfans_capture_website job.",
      "maxLength": 128
    }
  },
  "required": [
    "capture"
  ],
  "additionalProperties": false
}
⚪ugcfans_make_launch_film(capture, aspect)

Makes a 12-second launch film of the page's headline, button and picture from a finished capture, in the chosen frame, and returns a job. The result is an editable film; ugcfans_export_film renders it to MP4. Free of credits. A launch film has no text layers: its words are pictures of the page.

输入模式

{
  "type": "object",
  "properties": {
    "capture": {
      "type": "string",
      "description": "The capture id.",
      "maxLength": 128
    },
    "aspect": {
      "type": "string",
      "description": "The frame: 16:9 landscape, 9:16 vertical, 1:1 square.",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ]
    }
  },
  "required": [
    "capture",
    "aspect"
  ],
  "additionalProperties": false
}
🟡ugcfans_make_site_sting(capture, node_ids, aspect, key_phrase)

Makes a 12-second, 8-scene film from the page parts you choose (node_ids from ugcfans_get_capture), in the chosen frame. Unlike a launch film its page text stays as editable text, so ugcfans_set_film_words can change it. Free of credits. Returns the film and its first revision at once.

输入模式

{
  "type": "object",
  "properties": {
    "capture": {
      "type": "string",
      "description": "The capture id.",
      "maxLength": 128
    },
    "node_ids": {
      "type": "array",
      "description": "The node_id of each part to include, from ugcfans_get_capture.",
      "items": {
        "type": "string",
        "description": "A node_id.",
        "maxLength": 200
      },
      "minItems": 1,
      "maxItems": 100
    },
    "aspect": {
      "type": "string",
      "description": "The frame: 16:9 landscape, 9:16 vertical, 1:1 square.",
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ]
    },
    "key_phrase": {
      "type": "string",
      "description": "A phrase of the chosen text to feature. It must appear in the chosen parts.",
      "maxLength": 200
    }
  },
  "required": [
    "capture",
    "node_ids",
    "aspect"
  ],
  "additionalProperties": false
}
⚪ugcfans_ad_to_film(ad)

Makes an editable film from a finished video ad, so its captions and end card can be changed, and returns the film and its first revision. The ad must be finished, must not already be a film, must be a video and at most 96 MiB. Free of credits.

输入模式

{
  "type": "object",
  "properties": {
    "ad": {
      "type": "string",
      "description": "The ad id, from a finished ugcfans_make_ad job.",
      "maxLength": 128
    }
  },
  "required": [
    "ad"
  ],
  "additionalProperties": false
}
🟡ugcfans_set_film_words(film, revision, replacements)

Changes text in a film: every text layer whose words contain find gets replace, and the result is saved as a new revision; the earlier revision stays as it was. Films made by ugcfans_make_launch_film have no text layers, so nothing changes in them. Free of credits.

输入模式

{
  "type": "object",
  "properties": {
    "film": {
      "type": "string",
      "description": "The film id.",
      "maxLength": 128
    },
    "revision": {
      "type": "string",
      "description": "The revision to edit.",
      "maxLength": 128
    },
    "replacements": {
      "type": "array",
      "description": "Pairs of words to find and what to put in their place, applied in order.",
      "items": {
        "type": "object",
        "properties": {
          "find": {
            "type": "string",
            "description": "The words to find.",
            "minLength": 1,
            "maxLength": 400
          },
          "replace": {
            "type": "string",
            "description": "The words to put in their place.",
            "maxLength": 400
          }
        },
        "required": [
          "find",
          "replace"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 20
    }
  },
  "required": [
    "film",
    "revision",
    "replacements"
  ],
  "additionalProperties": false
}
⚪ugcfans_export_film(film, revision)

Renders one revision of a film to an MP4 with a content credential, and returns a job; when it is done the result carries a link to the file. Free of credits. A film with an unresolved rendering requirement cannot be exported.

输入模式

{
  "type": "object",
  "properties": {
    "film": {
      "type": "string",
      "description": "The film id.",
      "maxLength": 128
    },
    "revision": {
      "type": "string",
      "description": "The revision to render.",
      "maxLength": 128
    }
  },
  "required": [
    "film",
    "revision"
  ],
  "additionalProperties": false
}
🟡ugcfans_finish_clip(source, operations)

Runs up to 6 finishing operations in order on a clip of the library, each on the file the one before made: trim, reformat to another frame, burn in captions, overlay a brand logo, close with an end card, or mix in music. Returns the last job, whose result links the finished file. A call that runs past 4 minutes returns the job it is on and the operations still to run. Free of credits. The clip must already be in the library: upload footage at https://ugc.fans/library, then find its address with ugcfans_list_files. mix confirms the person may use the music file.

输入模式

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "The clip's address in the library, out/...",
      "maxLength": 512
    },
    "operations": {
      "type": "array",
      "description": "The operations, in order.",
      "items": {
        "type": "object",
        "properties": {
          "op": {
            "type": "string",
            "description": "What to do.",
            "enum": [
              "trim",
              "reformat",
              "captions",
              "overlay",
              "end_card",
              "mix"
            ]
          },
          "start": {
            "type": "number",
            "description": "trim: where to start, in seconds (default 0).",
            "minimum": 0
          },
          "end": {
            "type": "number",
            "description": "trim: where to stop, in seconds.",
            "minimum": 0
          },
          "aspect_ratio": {
            "type": "string",
            "description": "reformat: the new frame.",
            "enum": [
              "9:16",
              "1:1",
              "16:9",
              "4:5"
            ]
          },
          "mode": {
            "type": "string",
            "description": "reformat: crop the picture, pad it, or follow the subject (default crop).",
            "enum": [
              "crop",
              "pad",
              "follow"
            ]
          },
          "transcript": {
            "type": "string",
            "description": "captions: the id of a transcript from ugcfans_transcribe.",
            "maxLength": 128
          },
          "cues": {
            "type": "array",
            "description": "captions: the lines to show, each with start and end seconds and its text.",
            "items": {
              "type": "object",
              "properties": {
                "start": {
                  "type": "number",
                  "description": "Seconds.",
                  "minimum": 0
                },
                "end": {
                  "type": "number",
                  "description": "Seconds.",
                  "minimum": 0
                },
                "text": {
                  "type": "string",
                  "description": "The line.",
                  "maxLength": 400
                }
              },
              "required": [
                "start",
                "end",
                "text"
              ],
              "additionalProperties": false
            },
            "maxItems": 2000
          },
          "brand": {
            "type": "string",
            "description": "overlay and end_card: the id of a saved brand; overlay puts its logo in the top-right corner, and end_card uses its colours and logo.",
            "maxLength": 128
          },
          "headline": {
            "type": "string",
            "description": "end_card: the closing headline.",
            "maxLength": 200
          },
          "subline": {
            "type": "string",
            "description": "end_card: a second line.",
            "maxLength": 200
          },
          "music": {
            "type": "string",
            "description": "mix: the address of the music file, out/..., which the person has the right to use.",
            "maxLength": 512
          }
        },
        "required": [
          "op"
        ],
        "additionalProperties": false
      },
      "minItems": 1,
      "maxItems": 6
    }
  },
  "required": [
    "source",
    "operations"
  ],
  "additionalProperties": false
}
🟡ugcfans_transcribe(source)

Writes out the words of an audio or video file in the library, up to 10 minutes long, with the built-in speech model, and returns a job; when it is done the result has the transcript id, its text, the language and the length. The transcript id feeds the captions operation of ugcfans_finish_clip. Free of credits. Upload footage at https://ugc.fans/library first, then find its address with ugcfans_list_files.

输入模式

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "The file's address in the library, out/...",
      "maxLength": 512
    }
  },
  "required": [
    "source"
  ],
  "additionalProperties": false
}
🟢ugcfans_list_files(prefix, limit)

Lists files in the account's library, newest first: the path of each (out/...), its size and when it changed. Pictures, video, audio and fonts only. Free. Footage is added at https://ugc.fans/library; the path is what the clip and transcript tools take as source.

输入模式

{
  "type": "object",
  "properties": {
    "prefix": {
      "type": "string",
      "description": "Only paths that start with this, such as out/api/images. The default is the whole library, out.",
      "maxLength": 512
    },
    "limit": {
      "type": "integer",
      "description": "How many files to list, newest first.",
      "minimum": 1,
      "maximum": 100
    }
  },
  "required": [],
  "additionalProperties": false
}
⚪ugcfans_share_file(path, kind)

Makes a link that opens one file of the library for anyone who holds it, without signing in. A link lasts 6 hours; a showcase page, which carries the Made with UGC Fans badge, lasts 30 days. Free. Anyone with the link can see the file until it expires.

输入模式

{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "The file's address in the library, out/...",
      "maxLength": 512
    },
    "kind": {
      "type": "string",
      "description": "link opens the file itself (default); showcase is a page that shows it.",
      "enum": [
        "link",
        "showcase"
      ]
    }
  },
  "required": [
    "path"
  ],
  "additionalProperties": false
}
🟢ugcfans_get_job(job)

Reads where a job stands: working, done with its files as links, failed with the reason, or cancelled. Free. Works for any job the account started.

输入模式

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "The job id a tool returned, job_...",
      "maxLength": 128
    }
  },
  "required": [
    "job"
  ],
  "additionalProperties": false
}
🟢ugcfans_wait_job(job, seconds)

Waits up to 45 seconds for a job to finish and reports where it stands, as ugcfans_get_job does. It returns as soon as the job ends. Free.

输入模式

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "The job id a tool returned, job_...",
      "maxLength": 128
    },
    "seconds": {
      "type": "integer",
      "description": "How long to wait at most, up to 45 (default 45).",
      "minimum": 0,
      "maximum": 45
    }
  },
  "required": [
    "job"
  ],
  "additionalProperties": false
}
🔴ugcfans_cancel_job(job)

Stops a job that has not yet reached a provider; a cancelled job is not charged. A job that is already with a provider cannot be stopped and the call says so. Free.

输入模式

{
  "type": "object",
  "properties": {
    "job": {
      "type": "string",
      "description": "The job id a tool returned, job_...",
      "maxLength": 128
    }
  },
  "required": [
    "job"
  ],
  "additionalProperties": false
}
🟢ugcfans_list_models(kind)

Lists the image, video, voice and avatar models with the credits each costs per unit (an image, a clip, 1,000 characters) and whether a plan locks it. Free, and needs no sign-in. Signed out it is the whole price list; signed in it is the models on offer to this account, the ids ugcfans_estimate and the make tools accept.

输入模式

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "Only models of this kind.",
      "enum": [
        "image",
        "video",
        "voice",
        "avatar"
      ]
    }
  },
  "required": [],
  "additionalProperties": false
}
🟢ugcfans_estimate(kind, body)

Prices a request without making it: the most it can cost in credits, the dollar figures behind it, any warnings, and a quote that is good for about 10 minutes. Free. The body takes the same fields as ugcfans_make_ad, ugcfans_make_image or ugcfans_make_video, without the quote; the make tool takes the quote back and refuses it if any field changed.

输入模式

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "What is being priced.",
      "enum": [
        "ad",
        "image",
        "video"
      ]
    },
    "body": {
      "type": "object",
      "description": "The request: the fields of the make tool for this kind, without quote."
    }
  },
  "required": [
    "kind",
    "body"
  ],
  "additionalProperties": false
}
🟢ugcfans_make_image(model, prompt, reference, n, aspect_ratio, ...)

Makes a picture from a prompt, optionally following reference pictures, and returns a job; when it is done the result links the picture and a small one is shown inline. Spends the account's credits per picture (ugcfans_list_models gives each model's price). Call ugcfans_estimate first and pass its quote; without a quote this returns the cost and makes nothing.

输入模式

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model id, from ugcfans_list_models.",
      "maxLength": 200
    },
    "prompt": {
      "type": "string",
      "description": "What to draw, in words.",
      "maxLength": 4000
    },
    "reference": {
      "type": "array",
      "description": "Pictures of the subject or style to follow: addresses of library files, out/...",
      "items": {
        "type": "string",
        "description": "An address.",
        "maxLength": 512
      },
      "maxItems": 16
    },
    "n": {
      "type": "integer",
      "description": "How many pictures (default 1).",
      "minimum": 1,
      "maximum": 8
    },
    "aspect_ratio": {
      "type": "string",
      "description": "The frame, such as 1:1, 9:16 or 16:9, when the model offers it.",
      "maxLength": 20
    },
    "resolution": {
      "type": "string",
      "description": "The resolution, such as 1K, when the model offers it.",
      "maxLength": 20
    },
    "quote": {
      "type": "string",
      "description": "The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.",
      "maxLength": 4096
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}
🟢ugcfans_make_video(model, prompt, start_image, duration, aspect_ratio, ...)

Makes a video clip from a prompt, optionally beginning on a still, and returns a job; when it is done the result links the clip. Spends the account's credits per clip (ugcfans_list_models gives each model's price). Call ugcfans_estimate first and pass its quote; without a quote this returns the cost and makes nothing.

输入模式

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model id, from ugcfans_list_models.",
      "maxLength": 200
    },
    "prompt": {
      "type": "string",
      "description": "What happens, in words.",
      "maxLength": 4000
    },
    "start_image": {
      "type": "string",
      "description": "A picture to begin on: the address of a library file, out/...",
      "maxLength": 512
    },
    "duration": {
      "type": "integer",
      "description": "The length in seconds, from the lengths the model offers.",
      "minimum": 1,
      "maximum": 60
    },
    "aspect_ratio": {
      "type": "string",
      "description": "The frame, such as 9:16 or 16:9, when the model offers it.",
      "maxLength": 20
    },
    "resolution": {
      "type": "string",
      "description": "The resolution, such as 720p, when the model offers it.",
      "maxLength": 20
    },
    "quote": {
      "type": "string",
      "description": "The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.",
      "maxLength": 4096
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}
⚪ugcfans_make_ad(feature, template, product, person, voice, ...)

Makes a UGC-style ad from a product and a template or feature (testimonial, talking presenter, product video and others) and returns a job; when it is done the result lists the ad's files as links. Spends the account's credits; the cost depends on the feature and its length, so call ugcfans_estimate first and pass its quote. Without a quote this returns the cost and makes nothing. A presenter must be saved, have a portrait and, for a real person, recorded consent at https://ugc.fans/library.

输入模式

{
  "type": "object",
  "properties": {
    "feature": {
      "type": "string",
      "description": "What kind of ad, a slug from ugcfans_search_templates such as testimonial, talking-presenter or product-video.",
      "maxLength": 64
    },
    "template": {
      "type": "string",
      "description": "A template slug from ugcfans_search_templates, which fills in the frame, length and shots.",
      "maxLength": 64
    },
    "product": {
      "description": "What is being sold: a sentence, or an object with its name, description and pictures.",
      "anyOf": [
        {
          "type": "string",
          "maxLength": 1200
        },
        {
          "type": "object",
          "properties": {
            "name": {
              "type": "string",
              "description": "The product's name.",
              "maxLength": 200
            },
            "description": {
              "type": "string",
              "description": "What it is and does.",
              "maxLength": 1000
            },
            "images": {
              "type": "array",
              "description": "Pictures of it: addresses of library files, out/...",
              "items": {
                "type": "string",
                "description": "An address.",
                "maxLength": 512
              },
              "maxItems": 12
            }
          },
          "required": [
            "name"
          ],
          "additionalProperties": false
        }
      ]
    },
    "person": {
      "type": "string",
      "description": "The presenter: the id of a saved person that has a portrait and, for a real person, recorded consent.",
      "maxLength": 128
    },
    "voice": {
      "type": "string",
      "description": "The voice: the id of a saved voice.",
      "maxLength": 128
    },
    "script": {
      "type": "string",
      "description": "A script already written, by its id from ugcfans_write_script.",
      "maxLength": 128
    },
    "page_url": {
      "type": "string",
      "description": "A web page to read the product from.",
      "maxLength": 2048
    },
    "testimonial_basis": {
      "type": "string",
      "description": "Where a testimonial's words come from. verbatim and edited need reviews.",
      "enum": [
        "verbatim",
        "edited",
        "composed"
      ]
    },
    "reviews": {
      "type": "array",
      "description": "Real customer reviews a testimonial rests on.",
      "items": {
        "type": "string",
        "description": "A review.",
        "maxLength": 800
      },
      "maxItems": 12
    },
    "name": {
      "type": "string",
      "description": "A name for the ad.",
      "maxLength": 80
    },
    "quote": {
      "type": "string",
      "description": "The quote from ugcfans_estimate for exactly this request. Without it the call returns the estimate and makes nothing.",
      "maxLength": 4096
    }
  },
  "required": [
    "feature"
  ],
  "additionalProperties": false
}
🟡ugcfans_write_script(product, page_url, audience, offer, points, ...)

Writes an ad script from a product or a web page, or, given a saved script, writes alternative opening hooks for it or translates it, and returns a job whose result holds the script. Spends a few of the account's credits. Give product or page_url to write a new script; give script with hooks (how many) or with translate_to (a language) to work on one.

输入模式

{
  "type": "object",
  "properties": {
    "product": {
      "type": "string",
      "description": "What is being sold, in a sentence or two.",
      "maxLength": 1200
    },
    "page_url": {
      "type": "string",
      "description": "A web page to read the product from, instead of product.",
      "maxLength": 2048
    },
    "audience": {
      "type": "string",
      "description": "Who the ad is for.",
      "maxLength": 400
    },
    "offer": {
      "type": "string",
      "description": "The offer or call to action.",
      "maxLength": 300
    },
    "points": {
      "type": "array",
      "description": "Points the script should make.",
      "items": {
        "type": "string",
        "description": "A point.",
        "maxLength": 300
      },
      "maxItems": 12
    },
    "seconds": {
      "type": "integer",
      "description": "How long the ad runs, 5 to 120 (default 30).",
      "minimum": 5,
      "maximum": 120
    },
    "angle": {
      "type": "string",
      "description": "The angle or hook to take.",
      "maxLength": 200
    },
    "language": {
      "type": "string",
      "description": "The language to write in (default English).",
      "maxLength": 40
    },
    "brand": {
      "type": "string",
      "description": "The id of a saved brand whose voice to follow.",
      "maxLength": 128
    },
    "script": {
      "type": "string",
      "description": "The id of a saved script to work on, from an earlier ugcfans_write_script.",
      "maxLength": 128
    },
    "hooks": {
      "type": "integer",
      "description": "With script: how many alternative openings to write.",
      "minimum": 1,
      "maximum": 12
    },
    "translate_to": {
      "type": "string",
      "description": "With script: the language to translate it into.",
      "maxLength": 40
    }
  },
  "required": [],
  "additionalProperties": false
}
⚪ugcfans_make_speech(voice, text, script, speed, quote)

Speaks a line or a saved script in a saved voice and returns a job whose result links the audio. Spends a few of the account's credits. Without a quote the call prices the line first and, when the pipeline can price it, makes it; a voice that cannot be priced ahead cannot be made here. A cloned voice needs its owner's recorded consent.

输入模式

{
  "type": "object",
  "properties": {
    "voice": {
      "type": "string",
      "description": "The id of a saved voice, voice_...",
      "maxLength": 128
    },
    "text": {
      "type": "string",
      "description": "The words to speak.",
      "maxLength": 5000
    },
    "script": {
      "type": "string",
      "description": "Or the id of a saved script to speak.",
      "maxLength": 128
    },
    "speed": {
      "type": "number",
      "description": "How fast, 0.5 to 1.5 (default 1).",
      "minimum": 0.5,
      "maximum": 1.5
    },
    "quote": {
      "type": "string",
      "description": "A quote for exactly this line, when you hold one.",
      "maxLength": 4096
    }
  },
  "required": [
    "voice"
  ],
  "additionalProperties": false
}
🟢ugcfans_make_performance(kind, person, speech, script, text, ...)

Puts a saved person on screen and returns a job: talking has them speak a line, motion has them move as a reference clip moves, swap puts them in place of the person in a clip, and product shows them holding a product (a picture). Spends the account's credits; a talking clip costs about what its avatar model costs (ugcfans_list_models, kind avatar). The person must be saved with a portrait and, if real, recorded consent at https://ugc.fans/library. motion and swap need rights_confirmed: true, given only after the person confirms they may use the source clip.

输入模式

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "What to make.",
      "enum": [
        "talking",
        "motion",
        "swap",
        "product"
      ]
    },
    "person": {
      "type": "string",
      "description": "The id of the saved person.",
      "maxLength": 128
    },
    "speech": {
      "type": "string",
      "description": "talking: the id of a saved line to use as the audio.",
      "maxLength": 128
    },
    "script": {
      "type": "string",
      "description": "talking: the id of a saved script to speak.",
      "maxLength": 128
    },
    "text": {
      "type": "string",
      "description": "talking: words to speak.",
      "maxLength": 5000
    },
    "voice": {
      "type": "string",
      "description": "talking, with script or text: the id of the saved voice to speak in.",
      "maxLength": 128
    },
    "image": {
      "type": "string",
      "description": "talking: which picture of the person to use, out/...",
      "maxLength": 512
    },
    "source": {
      "type": "string",
      "description": "motion and swap: the reference clip's address, out/...",
      "maxLength": 512
    },
    "rights_confirmed": {
      "type": "boolean",
      "description": "motion and swap: the person confirms they may use the source clip."
    },
    "motion_from": {
      "type": "string",
      "description": "motion: follow the clip itself or its pose (default clip).",
      "enum": [
        "clip",
        "pose"
      ]
    },
    "note": {
      "type": "string",
      "description": "swap: what to change, in words.",
      "maxLength": 400
    },
    "product": {
      "type": "string",
      "description": "product: the product's name.",
      "maxLength": 200
    },
    "product_images": {
      "type": "array",
      "description": "product: pictures of the product, out/...",
      "items": {
        "type": "string",
        "description": "An address.",
        "maxLength": 512
      },
      "maxItems": 3
    },
    "brand": {
      "type": "string",
      "description": "product: the id of a saved brand whose kit holds the product pictures.",
      "maxLength": 128
    },
    "handling": {
      "type": "string",
      "description": "product: how the person has it.",
      "enum": [
        "held",
        "worn",
        "used",
        "beside"
      ]
    },
    "setting": {
      "type": "string",
      "description": "motion and product: where it happens.",
      "maxLength": 300
    }
  },
  "required": [
    "kind",
    "person"
  ],
  "additionalProperties": false
}
🟡ugcfans_read_reference(source)

Reads a reference video of up to 3 minutes in the library and returns a job whose result is its breakdown: hook, structure, shots, pacing and look, with still frames, and none of its footage, sound or words. Spends a few of the account's credits. Using it confirms the person may study the file. Upload the video at https://ugc.fans/library first.

输入模式

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "The video's address in the library, out/...",
      "maxLength": 512
    }
  },
  "required": [
    "source"
  ],
  "additionalProperties": false
}
🟡ugcfans_save_asset(kind, name, brand, product, description, ...)

Saves a brand kit, a product, a generated presenter or a stock voice to the library for reuse in ads, and returns its id. Free. Only generated presenters (described in words, not a real person) and stock voices can be saved here: a real person's face or voice needs the consent the person records at https://ugc.fans/library. A new presenter has no picture until its portrait is drawn there.

输入模式

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string",
      "description": "What to save.",
      "enum": [
        "brand",
        "product",
        "person",
        "voice"
      ]
    },
    "name": {
      "type": "string",
      "description": "Its name.",
      "maxLength": 80
    },
    "brand": {
      "type": "string",
      "description": "product: the id of the brand it belongs to.",
      "maxLength": 128
    },
    "product": {
      "type": "string",
      "description": "brand: what the brand sells.",
      "maxLength": 600
    },
    "description": {
      "type": "string",
      "description": "product: what it is. person: who the presenter is, drawn from these words.",
      "maxLength": 1200
    },
    "url": {
      "type": "string",
      "description": "brand and product: their web address.",
      "maxLength": 300
    },
    "tone": {
      "type": "string",
      "description": "brand: its voice, such as warm and plain.",
      "maxLength": 400
    },
    "tagline": {
      "type": "string",
      "description": "brand: its tagline.",
      "maxLength": 160
    },
    "call_to_action": {
      "type": "string",
      "description": "brand: what an ad asks the viewer to do.",
      "maxLength": 80
    },
    "palette": {
      "type": "object",
      "properties": {
        "primary": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        },
        "secondary": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        },
        "text": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        },
        "background": {
          "type": "string",
          "description": "A colour, #RRGGBB.",
          "maxLength": 7
        }
      },
      "required": [],
      "additionalProperties": false
    },
    "logo": {
      "type": "string",
      "description": "brand: the address of its logo, out/...",
      "maxLength": 512
    },
    "never": {
      "type": "array",
      "description": "brand: words and claims its ads never use.",
      "items": {
        "type": "string",
        "description": "A word or claim.",
        "maxLength": 200
      },
      "maxItems": 50
    },
    "images": {
      "type": "array",
      "description": "brand and product: addresses of product pictures, out/...",
      "items": {
        "type": "string",
        "description": "An address.",
        "maxLength": 512
      },
      "maxItems": 12
    },
    "claims": {
      "type": "array",
      "description": "product: claims an ad may make about it.",
      "items": {
        "type": "string",
        "description": "A claim.",
        "maxLength": 200
      },
      "maxItems": 12
    },
    "provider_voice": {
      "type": "string",
      "description": "voice: the stock voice's name, from the speech models.",
      "maxLength": 200
    },
    "language": {
      "type": "string",
      "description": "voice: its language, as a tag such as en-US.",
      "maxLength": 35
    }
  },
  "required": [
    "kind",
    "name"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本26 个工具