{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-api-transit-station",
    "name": "API-Station",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/QB-Chen/ai-api-transit-station",
    "canonicalUrl": "https://clawhub.ai/QB-Chen/ai-api-transit-station",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-api-transit-station",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-api-transit-station",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/ai-api-transit-station"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/ai-api-transit-station",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-api-transit-station/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-api-transit-station/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-api-transit-station/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "伝富AI-API 调用技能",
        "body": "本技能帮助你调用伝富AI-API平台的302+个API接口。当用户需要调用AI能力时，使用此技能。"
      },
      {
        "title": "🔐 关键地址配置",
        "body": "[!IMPORTANT]\n请注意区分以下三个关键地址：\n\n类型地址说明API请求地址https://api.winfull.cloud-ip.cc以此开头调用所有接口 (Base URL)API官网/Tokenhttps://api.winfull.cloud-ip.cc/在此注册账户、充值、申请API TokenAPI文档地址https://winfull.apifox.cn/查阅最新的接口文档、参数说明\n\n认证方式: 所有请求必须在Header中携带Bearer Token\n\nAuthorization: Bearer sk-xxxxxxxx"
      },
      {
        "title": "📚 API分类速查",
        "body": "完整文档地址：https://winfull.apifox.cn/\n\n类别接口数说明图像生成82DALL·E、Flux、豆包、Ideogram、Imagen视频生成54Sora、Veo、可灵、即梦、Minimax聊天43GPT、Claude、Gemini、DeepSeek任务查询33异步任务查询其他24文件上传、模型列表、代码执行等函数调用12Function Calling、Web搜索Replicate12Replicate平台模型音乐生成9Suno音乐生成Midjourney8Midjourney完整功能音频7TTS、Whisper、音频理解系统API7Token管理、用户信息可灵Kling6可灵专属功能文档处理3PDF理解、文档解析嵌入2Embeddings向量化\n\n总计: 302+ 个API接口"
      },
      {
        "title": "1. 聊天补全 (Chat Completions)",
        "body": "端点: POST /v1/chat/completions\n\nimport requests\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/chat/completions\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"gpt-5.2\",\n        \"messages\": [\n            {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n            {\"role\": \"user\", \"content\": \"你好\"}\n        ]\n    }\n)\n\nresult = response.json()\nprint(result[\"choices\"][0][\"message\"][\"content\"])"
      },
      {
        "title": "2. 图像生成 (Image Generations)",
        "body": "端点: POST /v1/images/generations\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/images/generations\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"gpt-image-1.5-all\",\n        \"prompt\": \"一只可爱的猫咪在草地上\",\n        \"size\": \"1024x1536\"\n    }\n)\n\nresult = response.json()\nimage_url = result[\"data\"][0][\"url\"]"
      },
      {
        "title": "3. 图片上传到图床",
        "body": "[!IMPORTANT]\n图生视频必读: 如果需要使用本地图片生成视频，必须先将图片上传到图床获取公网URL，然后使用该URL传给视频生成接口。\n两种方式:\n\n上传本地图片到图床（推荐）\n直接使用已有的公网图片地址\n\n端点: POST https://imageproxy.zhongzhuan.chat/api/upload\n\n# 方式1: 上传本地图片到图床\nwith open(\"reference_image.jpg\", \"rb\") as f:\n    response = requests.post(\n        \"https://imageproxy.zhongzhuan.chat/api/upload\",\n        headers={\"Authorization\": \"Bearer sk-xxx\"},\n        files={\"file\": f}\n    )\n\nresult = response.json()\nimage_url = result[\"url\"]  # 获取图床URL\nprint(f\"图片已上传: {image_url}\")\n\n# 方式2: 直接使用公网图片地址\n# image_url = \"https://example.com/your-image.jpg\"\n\n# 现在可以使用这个URL进行图生视频\n\ncurl示例:\n\ncurl --location --request POST 'https://imageproxy.zhongzhuan.chat/api/upload' \\\n--header 'Authorization: Bearer <token>' \\\n--form 'file=@\"/path/to/your/image.png\"'"
      },
      {
        "title": "4. 视频生成 (异步任务)",
        "body": "创建视频: POST /v1/video/create\n\nimport time\n\n# 如果需要使用参考图，先上传图片到图床\nimage_url = None\nif use_reference_image:\n    with open(\"reference.jpg\", \"rb\") as f:\n        upload_response = requests.post(\n            \"https://imageproxy.zhongzhuan.chat/api/upload\",\n            headers={\"Authorization\": \"Bearer sk-xxx\"},\n            files={\"file\": f}\n        )\n    image_url = upload_response.json()[\"url\"]\n    print(f\"参考图已上传: {image_url}\")\n\n# 步骤1: 创建视频任务\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/video/create\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"sora-2\",\n        \"prompt\": \"一只小狗在草地上奔跑\",\n        \"images\": [image_url] if image_url else [],  # 使用图床URL\n        \"orientation\": \"portrait\",\n        \"duration\": 15\n    }\n)\n\nresult = response.json()\ntask_id = result[\"id\"]\n\n查询任务: GET /v1/video/query?id={task_id}\n\n# 步骤2: 轮询查询任务状态\nwhile True:\n    result = requests.get(\n        f\"https://api.winfull.cloud-ip.cc/v1/video/query?id={task_id}\",\n        headers={\"Authorization\": \"Bearer sk-xxx\"}\n    ).json()\n    \n    if result[\"status\"] == \"completed\":\n        video_url = result[\"video_url\"]\n        print(f\"视频生成成功: {video_url}\")\n        break\n    elif result[\"status\"] == \"failed\":\n        raise Exception(f\"视频生成失败: {result.get('error')}\")\n    \n    time.sleep(5)"
      },
      {
        "title": "5. 语音合成 (TTS)",
        "body": "端点: POST /v1/audio/speech\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/audio/speech\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"tts-1\",\n        \"input\": \"你好，世界！\",\n        \"voice\": \"alloy\"\n    }\n)\n\nwith open(\"output.mp3\", \"wb\") as f:\n    f.write(response.content)"
      },
      {
        "title": "6. 语音识别 (Whisper)",
        "body": "端点: POST /v1/audio/transcriptions\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/audio/transcriptions\",\n    headers={\"Authorization\": \"Bearer sk-xxx\"},\n    files={\"file\": open(\"audio.mp3\", \"rb\")},\n    data={\"model\": \"whisper-1\"}\n)\n\nresult = response.json()\ntranscribed_text = result[\"text\"]"
      },
      {
        "title": "7. Midjourney",
        "body": "提交Imagine任务: POST /mj/submit/imagine\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/mj/submit/imagine\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"prompt\": \"a beautiful sunset over the ocean --ar 16:9 --v 6\"\n    }\n)\n\nresult = response.json()\ntask_id = result[\"result\"]"
      },
      {
        "title": "📋 异步任务通用流程",
        "body": "大多数生成类API（视频、音乐、部分图像）都是异步的：\n\n创建任务 → 获取task_id\n轮询查询状态 (pending/processing)\n状态变为completed → 获取结果URL\n状态变为failed → 处理错误\n\n轮询建议: 间隔5-10秒查询一次任务状态"
      },
      {
        "title": "⚠️ 重要注意事项",
        "body": "认证方式: 所有请求必须在Header中携带 Authorization: Bearer sk-xxxxxxxx\n图生视频流程:\n\n本地图片必须先上传到图床: https://imageproxy.zhongzhuan.chat/api/upload\n或使用已有的公网图片URL\n然后将URL传给视频生成接口的 images 参数\n\n\n异步轮询: 视频/音乐生成需要轮询，间隔建议5-10秒\nBase URL: 所有接口都以 https://api.winfull.cloud-ip.cc 开头\n速率限制: 合理控制请求频率，避免触发限流\nToken计费: 不同模型计费标准不同，详见官网"
      },
      {
        "title": "📖 详细文档参考",
        "body": "在线API文档: https://winfull.apifox.cn/\n完整接口列表: 查看 api_list.md 文件\n官网/Token管理: https://api.winfull.cloud-ip.cc/"
      },
      {
        "title": "Q1: 如何获取API Token?",
        "body": "访问 https://api.winfull.cloud-ip.cc/ 注册账户，在控制台中申请API Token。"
      },
      {
        "title": "Q2: 如何使用本地图片生成视频?",
        "body": "必须先将本地图片上传到图床：\n\n# 1. 上传图片到图床\nwith open(\"image.jpg\", \"rb\") as f:\n    upload_resp = requests.post(\n        \"https://imageproxy.zhongzhuan.chat/api/upload\",\n        headers={\"Authorization\": \"Bearer sk-xxx\"},\n        files={\"file\": f}\n    )\nimage_url = upload_resp.json()[\"url\"]\n\n# 2. 使用图片URL创建视频\nvideo_resp = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/video/create\",\n    headers={\"Authorization\": \"Bearer sk-xxx\", \"Content-Type\": \"application/json\"},\n    json={\"model\": \"sora-2\", \"prompt\": \"描述\", \"images\": [image_url]}\n)"
      },
      {
        "title": "Q3: 可以直接使用公网图片URL吗?",
        "body": "可以！如果图片已经在公网上，可以直接使用URL，无需上传：\n\nimage_url = \"https://example.com/your-image.jpg\"\n# 直接使用这个URL创建视频"
      },
      {
        "title": "Q4: 异步任务一直处于pending状态怎么办?",
        "body": "检查任务ID是否正确\n等待更长时间（某些模型生成较慢）\n查看账户余额是否充足\n联系技术支持"
      },
      {
        "title": "Q5: 视频生成需要多长时间?",
        "body": "根据模型和视频长度不同，通常需要1-10分钟。建议每5-10秒轮询一次任务状态。"
      }
    ],
    "body": "伝富AI-API 调用技能\n\n本技能帮助你调用伝富AI-API平台的302+个API接口。当用户需要调用AI能力时，使用此技能。\n\n🔐 关键地址配置\n\n[!IMPORTANT] 请注意区分以下三个关键地址：\n\n类型\t地址\t说明\nAPI请求地址\thttps://api.winfull.cloud-ip.cc\t以此开头调用所有接口 (Base URL)\nAPI官网/Token\thttps://api.winfull.cloud-ip.cc/\t在此注册账户、充值、申请API Token\nAPI文档地址\thttps://winfull.apifox.cn/\t查阅最新的接口文档、参数说明\n\n认证方式: 所有请求必须在Header中携带Bearer Token\n\nAuthorization: Bearer sk-xxxxxxxx\n\n📚 API分类速查\n\n完整文档地址：https://winfull.apifox.cn/\n\n类别\t接口数\t说明\n图像生成\t82\tDALL·E、Flux、豆包、Ideogram、Imagen\n视频生成\t54\tSora、Veo、可灵、即梦、Minimax\n聊天\t43\tGPT、Claude、Gemini、DeepSeek\n任务查询\t33\t异步任务查询\n其他\t24\t文件上传、模型列表、代码执行等\n函数调用\t12\tFunction Calling、Web搜索\nReplicate\t12\tReplicate平台模型\n音乐生成\t9\tSuno音乐生成\nMidjourney\t8\tMidjourney完整功能\n音频\t7\tTTS、Whisper、音频理解\n系统API\t7\tToken管理、用户信息\n可灵Kling\t6\t可灵专属功能\n文档处理\t3\tPDF理解、文档解析\n嵌入\t2\tEmbeddings向量化\n\n总计: 302+ 个API接口\n\n🚀 核心API调用模式\n1. 聊天补全 (Chat Completions)\n\n端点: POST /v1/chat/completions\n\nimport requests\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/chat/completions\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"gpt-5.2\",\n        \"messages\": [\n            {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n            {\"role\": \"user\", \"content\": \"你好\"}\n        ]\n    }\n)\n\nresult = response.json()\nprint(result[\"choices\"][0][\"message\"][\"content\"])\n\n2. 图像生成 (Image Generations)\n\n端点: POST /v1/images/generations\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/images/generations\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"gpt-image-1.5-all\",\n        \"prompt\": \"一只可爱的猫咪在草地上\",\n        \"size\": \"1024x1536\"\n    }\n)\n\nresult = response.json()\nimage_url = result[\"data\"][0][\"url\"]\n\n3. 图片上传到图床\n\n[!IMPORTANT] 图生视频必读: 如果需要使用本地图片生成视频，必须先将图片上传到图床获取公网URL，然后使用该URL传给视频生成接口。\n\n两种方式:\n\n上传本地图片到图床（推荐）\n直接使用已有的公网图片地址\n\n端点: POST https://imageproxy.zhongzhuan.chat/api/upload\n\n# 方式1: 上传本地图片到图床\nwith open(\"reference_image.jpg\", \"rb\") as f:\n    response = requests.post(\n        \"https://imageproxy.zhongzhuan.chat/api/upload\",\n        headers={\"Authorization\": \"Bearer sk-xxx\"},\n        files={\"file\": f}\n    )\n\nresult = response.json()\nimage_url = result[\"url\"]  # 获取图床URL\nprint(f\"图片已上传: {image_url}\")\n\n# 方式2: 直接使用公网图片地址\n# image_url = \"https://example.com/your-image.jpg\"\n\n# 现在可以使用这个URL进行图生视频\n\n\ncurl示例:\n\ncurl --location --request POST 'https://imageproxy.zhongzhuan.chat/api/upload' \\\n--header 'Authorization: Bearer <token>' \\\n--form 'file=@\"/path/to/your/image.png\"'\n\n4. 视频生成 (异步任务)\n\n创建视频: POST /v1/video/create\n\nimport time\n\n# 如果需要使用参考图，先上传图片到图床\nimage_url = None\nif use_reference_image:\n    with open(\"reference.jpg\", \"rb\") as f:\n        upload_response = requests.post(\n            \"https://imageproxy.zhongzhuan.chat/api/upload\",\n            headers={\"Authorization\": \"Bearer sk-xxx\"},\n            files={\"file\": f}\n        )\n    image_url = upload_response.json()[\"url\"]\n    print(f\"参考图已上传: {image_url}\")\n\n# 步骤1: 创建视频任务\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/video/create\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"sora-2\",\n        \"prompt\": \"一只小狗在草地上奔跑\",\n        \"images\": [image_url] if image_url else [],  # 使用图床URL\n        \"orientation\": \"portrait\",\n        \"duration\": 15\n    }\n)\n\nresult = response.json()\ntask_id = result[\"id\"]\n\n\n查询任务: GET /v1/video/query?id={task_id}\n\n# 步骤2: 轮询查询任务状态\nwhile True:\n    result = requests.get(\n        f\"https://api.winfull.cloud-ip.cc/v1/video/query?id={task_id}\",\n        headers={\"Authorization\": \"Bearer sk-xxx\"}\n    ).json()\n    \n    if result[\"status\"] == \"completed\":\n        video_url = result[\"video_url\"]\n        print(f\"视频生成成功: {video_url}\")\n        break\n    elif result[\"status\"] == \"failed\":\n        raise Exception(f\"视频生成失败: {result.get('error')}\")\n    \n    time.sleep(5)\n\n5. 语音合成 (TTS)\n\n端点: POST /v1/audio/speech\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/audio/speech\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"model\": \"tts-1\",\n        \"input\": \"你好，世界！\",\n        \"voice\": \"alloy\"\n    }\n)\n\nwith open(\"output.mp3\", \"wb\") as f:\n    f.write(response.content)\n\n6. 语音识别 (Whisper)\n\n端点: POST /v1/audio/transcriptions\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/audio/transcriptions\",\n    headers={\"Authorization\": \"Bearer sk-xxx\"},\n    files={\"file\": open(\"audio.mp3\", \"rb\")},\n    data={\"model\": \"whisper-1\"}\n)\n\nresult = response.json()\ntranscribed_text = result[\"text\"]\n\n7. Midjourney\n\n提交Imagine任务: POST /mj/submit/imagine\n\nresponse = requests.post(\n    \"https://api.winfull.cloud-ip.cc/mj/submit/imagine\",\n    headers={\n        \"Authorization\": \"Bearer sk-xxx\",\n        \"Content-Type\": \"application/json\"\n    },\n    json={\n        \"prompt\": \"a beautiful sunset over the ocean --ar 16:9 --v 6\"\n    }\n)\n\nresult = response.json()\ntask_id = result[\"result\"]\n\n📋 异步任务通用流程\n\n大多数生成类API（视频、音乐、部分图像）都是异步的：\n\n创建任务 → 获取task_id\n轮询查询状态 (pending/processing)\n状态变为completed → 获取结果URL\n状态变为failed → 处理错误\n\n轮询建议: 间隔5-10秒查询一次任务状态\n\n⚠️ 重要注意事项\n认证方式: 所有请求必须在Header中携带 Authorization: Bearer sk-xxxxxxxx\n图生视频流程:\n本地图片必须先上传到图床: https://imageproxy.zhongzhuan.chat/api/upload\n或使用已有的公网图片URL\n然后将URL传给视频生成接口的 images 参数\n异步轮询: 视频/音乐生成需要轮询，间隔建议5-10秒\nBase URL: 所有接口都以 https://api.winfull.cloud-ip.cc 开头\n速率限制: 合理控制请求频率，避免触发限流\nToken计费: 不同模型计费标准不同，详见官网\n📖 详细文档参考\n在线API文档: https://winfull.apifox.cn/\n完整接口列表: 查看 api_list.md 文件\n官网/Token管理: https://api.winfull.cloud-ip.cc/\n❓ 常见问题\nQ1: 如何获取API Token?\n\n访问 https://api.winfull.cloud-ip.cc/ 注册账户，在控制台中申请API Token。\n\nQ2: 如何使用本地图片生成视频?\n\n必须先将本地图片上传到图床：\n\n# 1. 上传图片到图床\nwith open(\"image.jpg\", \"rb\") as f:\n    upload_resp = requests.post(\n        \"https://imageproxy.zhongzhuan.chat/api/upload\",\n        headers={\"Authorization\": \"Bearer sk-xxx\"},\n        files={\"file\": f}\n    )\nimage_url = upload_resp.json()[\"url\"]\n\n# 2. 使用图片URL创建视频\nvideo_resp = requests.post(\n    \"https://api.winfull.cloud-ip.cc/v1/video/create\",\n    headers={\"Authorization\": \"Bearer sk-xxx\", \"Content-Type\": \"application/json\"},\n    json={\"model\": \"sora-2\", \"prompt\": \"描述\", \"images\": [image_url]}\n)\n\nQ3: 可以直接使用公网图片URL吗?\n\n可以！如果图片已经在公网上，可以直接使用URL，无需上传：\n\nimage_url = \"https://example.com/your-image.jpg\"\n# 直接使用这个URL创建视频\n\nQ4: 异步任务一直处于pending状态怎么办?\n检查任务ID是否正确\n等待更长时间（某些模型生成较慢）\n查看账户余额是否充足\n联系技术支持\nQ5: 视频生成需要多长时间?\n\n根据模型和视频长度不同，通常需要1-10分钟。建议每5-10秒轮询一次任务状态。"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/QB-Chen/ai-api-transit-station",
    "publisherUrl": "https://clawhub.ai/QB-Chen/ai-api-transit-station",
    "owner": "QB-Chen",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-api-transit-station",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-api-transit-station",
    "agentUrl": "https://openagent3.xyz/skills/ai-api-transit-station/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-api-transit-station/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-api-transit-station/agent.md"
  }
}