[{"data":1,"prerenderedAt":500},["ShallowReactive",2],{"guide-\u002Fguides-zh\u002Foverview":3,"developer-code-eb0qrl":495,"developer-code-r5o41j":496,"developer-code-1kb15yj":497,"developer-code-1kdaqai":498,"developer-code-13r784n":499},{"id":4,"title":5,"body":6,"description":486,"extension":487,"meta":488,"navigation":489,"path":491,"seo":492,"stem":493,"__hash__":494},"guidesZh\u002Fguides-zh\u002Foverview.md","VisionStory API 概览",{"type":7,"value":8,"toc":474},"minimark",[9,13,18,21,69,72,83,92,103,110,186,190,195,198,229,239,243,250,272,282,286,293,297,300,322,329,333,340,388,420,423,427,451,455,470],[10,11,12],"p",{},"VisionStory API 是面向数字人视频和可编程 AI 媒体的 REST API。你可以从后端、自动化脚本或 AI Agent 中生成视频、语音和图像，克隆声音和数字人形象，转写音频、创建字幕，并管理可复用的媒体素材。",[14,15,17],"h2",{"id":16},"how-the-visionstory-api-works","VisionStory API 的工作方式",[10,19,20],{},"接入时遵循以下流程：",[22,23,24,32,47,60],"ol",{},[25,26,27,31],"li",{},[28,29,30],"strong",{},"查询资源"," — 获取当前可用的模型、数字人形象和声音。",[25,33,34,37,38,42,43,46],{},[28,35,36],{},"提交生成任务"," — ",[39,40,41],"code",{},"POST \u002Fapi\u002Fv1\u002Fvideo"," 会立即返回 ",[39,44,45],{},"video_id","。",[25,48,49,52,53,56,57,46],{},[28,50,51],{},"轮询任务状态"," — 调用 ",[39,54,55],{},"GET \u002Fapi\u002Fv1\u002Fvideo?video_id=...","，直到状态变为 ",[39,58,59],{},"created",[25,61,62,65,66,46],{},[28,63,64],{},"下载结果"," — 从响应中获取 ",[39,67,68],{},"video_url",[10,70,71],{},"所有请求使用同一个基础地址，并通过同一个请求头进行认证：",[73,74,81],"pre",{"className":75,"code":77,"filename":78,"language":79,"meta":80},[76],"language-text","X-API-Key: $VISIONSTORY_API_KEY\n","Request header","text","",[39,82,77],{"__ignoreMap":80},[10,84,85,88,89],{},[28,86,87],{},"基础地址："," ",[39,90,91],{},"https:\u002F\u002Fopenapi.visionstory.ai",[10,93,94,95,102],{},"在 ",[96,97,101],"a",{"href":98,"rel":99},"https:\u002F\u002Fdevelopers.visionstory.ai\u002Fapi-keys",[100],"nofollow","VisionStory API Key 页面","创建密钥。密钥应保存在服务端，不要暴露在浏览器代码或公开仓库中。",[10,104,105,106,109],{},"所有响应采用统一的外层结构。请求成功后，从顶层 ",[39,107,108],{},"data"," 字段读取结果：",[73,111,115],{"className":112,"code":113,"language":114,"meta":80,"style":80},"language-json shiki shiki-themes github-light github-dark","{\n  \"data\": {\n    \"video_id\": \"YOUR_VIDEO_ID\"\n  },\n  \"message\": \"success\",\n  \"server_time\": \"2026-08-20T06:15:18Z\"\n}\n","json",[39,116,117,126,136,149,155,169,180],{"__ignoreMap":80},[118,119,122],"span",{"class":120,"line":121},"line",1,[118,123,125],{"class":124},"sVt8B","{\n",[118,127,129,133],{"class":120,"line":128},2,[118,130,132],{"class":131},"sj4cs","  \"data\"",[118,134,135],{"class":124},": {\n",[118,137,139,142,145],{"class":120,"line":138},3,[118,140,141],{"class":131},"    \"video_id\"",[118,143,144],{"class":124},": ",[118,146,148],{"class":147},"sZZnC","\"YOUR_VIDEO_ID\"\n",[118,150,152],{"class":120,"line":151},4,[118,153,154],{"class":124},"  },\n",[118,156,158,161,163,166],{"class":120,"line":157},5,[118,159,160],{"class":131},"  \"message\"",[118,162,144],{"class":124},[118,164,165],{"class":147},"\"success\"",[118,167,168],{"class":124},",\n",[118,170,172,175,177],{"class":120,"line":171},6,[118,173,174],{"class":131},"  \"server_time\"",[118,176,144],{"class":124},[118,178,179],{"class":147},"\"2026-08-20T06:15:18Z\"\n",[118,181,183],{"class":120,"line":182},7,[118,184,185],{"class":124},"}\n",[14,187,189],{"id":188},"core-api-resources","核心 API 资源",[191,192,194],"h3",{"id":193},"avatar","数字人形象",[10,196,197],{},"数字人形象是视频中讲述脚本的角色。你可以使用公共形象库中的现成形象，也可以通过一张照片创建专属形象：",[73,199,203],{"className":200,"code":201,"language":202,"meta":80,"style":80},"language-bash shiki shiki-themes github-light github-dark","curl -s -H \"X-API-Key: $VISIONSTORY_API_KEY\" https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Favatars\n","bash",[39,204,205],{"__ignoreMap":80},[118,206,207,211,214,217,220,223,226],{"class":120,"line":121},[118,208,210],{"class":209},"sScJk","curl",[118,212,213],{"class":131}," -s",[118,215,216],{"class":131}," -H",[118,218,219],{"class":147}," \"X-API-Key: ",[118,221,222],{"class":124},"$VISIONSTORY_API_KEY",[118,224,225],{"class":147},"\"",[118,227,228],{"class":147}," https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Favatars\n",[10,230,231,232,235,236,46],{},"响应包含精选公共形象库 ",[39,233,234],{},"public_avatars","，以及你创建的形象 ",[39,237,238],{},"my_avatars",[191,240,242],{"id":241},"voice","声音",[10,244,245,246,249],{},"声音通过 ",[39,247,248],{},"voice_id"," 标识，用于将视频中的文本转换为语音。你可以从公共声音库中选择，也可以通过音频样本克隆自己的声音：",[73,251,253],{"className":200,"code":252,"language":202,"meta":80,"style":80},"curl -s -H \"X-API-Key: $VISIONSTORY_API_KEY\" https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Fvoices\n",[39,254,255],{"__ignoreMap":80},[118,256,257,259,261,263,265,267,269],{"class":120,"line":121},[118,258,210],{"class":209},[118,260,213],{"class":131},[118,262,216],{"class":131},[118,264,219],{"class":147},[118,266,222],{"class":124},[118,268,225],{"class":147},[118,270,271],{"class":147}," https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Fvoices\n",[10,273,274,275,278,279,46],{},"响应包含 ",[39,276,277],{},"public_voices"," 和 ",[39,280,281],{},"my_voices",[191,283,285],{"id":284},"audio-understanding","音频理解",[10,287,288,289,46],{},"将 WAV 或 MP3 语音转为文本、词级时间戳、说话人标签和 SRT 字幕，或将已知脚本与音频对齐。请求示例和计费方式见",[96,290,292],{"href":291},"\u002Fguides\u002Faudio-understanding","音频转写与对齐 API",[191,294,296],{"id":295},"credit","点数",[10,298,299],{},"点数是生成任务的计费单位，随 VisionStory 订阅提供。每次生成任务都会消耗点数，失败任务会自动退还。你可以随时查询余额：",[73,301,303],{"className":200,"code":302,"language":202,"meta":80,"style":80},"curl -s -H \"X-API-Key: $VISIONSTORY_API_KEY\" https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Fbilling\u002Fcredits\n",[39,304,305],{"__ignoreMap":80},[118,306,307,309,311,313,315,317,319],{"class":120,"line":121},[118,308,210],{"class":209},[118,310,213],{"class":131},[118,312,216],{"class":131},[118,314,219],{"class":147},[118,316,222],{"class":124},[118,318,225],{"class":147},[118,320,321],{"class":147}," https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Fbilling\u002Fcredits\n",[10,323,324,325,328],{},"数字人视频的状态响应通过 ",[39,326,327],{},"cost_credit"," 返回实际消耗的点数，方便你查看每个已完成任务的准确费用。",[14,330,332],{"id":331},"talking-avatar-models","数字人视频模型",[10,334,335,336,339],{},"数字人视频模型负责渲染角色。调用 ",[39,337,338],{},"GET \u002Fapi\u002Fv1\u002Fmodels"," 获取机器可读的模型目录。",[341,342,343,365],"table",{},[344,345,346],"thead",{},[347,348,349,353,356,359,362],"tr",{},[350,351,352],"th",{},"model_id",[350,354,355],{},"适用场景",[350,357,358],{},"画面比例",[350,360,361],{},"分辨率",[350,363,364],{},"最长时长",[366,367,368],"tbody",{},[347,369,370,376,379,382,385],{},[371,372,373],"td",{},[39,374,375],{},"vs_character_v4",[371,377,378],{},"推荐默认模型，动作质量和稳定性更好",[371,380,381],{},"9:16, 16:9, 1:1",[371,383,384],{},"720p, 1080p, 2k",[371,386,387],{},"600 秒",[10,389,390,391,394,395,397,398,401,402,405,406,409,410,413,414,416,417,419],{},"已下线的 ",[39,392,393],{},"vs_talk_v1"," 不再出现在模型目录中。新接入应从 ",[39,396,338],{}," 返回的选项中选择 ",[39,399,400],{},"720p","、",[39,403,404],{},"1080p"," 或 ",[39,407,408],{},"2k","。为兼容旧调用，API 仍接受旧版 ",[39,411,412],{},"480p"," 请求，并按 ",[39,415,400],{}," 渲染和计费；响应结构仍保留 ",[39,418,412],{},"，以准确表示历史视频。",[10,421,422],{},"除数字人视频外，API 还提供前沿 AI 视频生成模型，支持文生视频和图生视频。这些能力目前处于 Beta 阶段。",[14,424,426],{"id":425},"start-building-with-the-visionstory-api","开始接入 VisionStory API",[428,429,430,437,444],"ul",{},[25,431,432,436],{},[96,433,435],{"href":434},"\u002Fguides\u002Fquick-start","快速开始"," — 五步创建第一个视频。",[25,438,439,443],{},[96,440,442],{"href":441},"\u002Freference","API 参考"," — 查看可用接口、数据结构和示例。",[25,445,446,450],{},[96,447,449],{"href":98,"rel":448},[100],"获取 API Key"," — 配置服务端接入。",[14,452,454],{"id":453},"structured-media-understanding","结构化媒体理解",[10,456,457,458,461,462,466,467,46],{},"通过 ",[39,459,460],{},"POST \u002Fapi\u002Fv1\u002Fmedia\u002Funderstand"," 从图片、音频或视频中提取结构化 JSON。请求包含提示词、1–8 个媒体引用，以及顶层为对象的 JSON Schema。SDK、CLI 与 MCP 示例见",[96,463,465],{"href":464},"\u002Fguides\u002Fmedia-understanding","媒体理解","；音频转写和字幕时间戳请使用",[96,468,469],{"href":291},"语音转文字",[471,472,473],"style",{},"html pre.shiki code .sVt8B, html code.shiki .sVt8B{--shiki-default:#24292E;--shiki-dark:#E1E4E8}html pre.shiki code .sj4cs, html code.shiki .sj4cs{--shiki-default:#005CC5;--shiki-dark:#79B8FF}html pre.shiki code .sZZnC, html code.shiki .sZZnC{--shiki-default:#032F62;--shiki-dark:#9ECBFF}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html pre.shiki code .sScJk, html code.shiki .sScJk{--shiki-default:#6F42C1;--shiki-dark:#B392F0}",{"title":80,"searchDepth":128,"depth":128,"links":475},[476,477,483,484,485],{"id":16,"depth":128,"text":17},{"id":188,"depth":128,"text":189,"children":478},[479,480,481,482],{"id":193,"depth":138,"text":194},{"id":241,"depth":138,"text":242},{"id":284,"depth":138,"text":285},{"id":295,"depth":138,"text":296},{"id":331,"depth":128,"text":332},{"id":425,"depth":128,"text":426},{"id":453,"depth":128,"text":454},"了解 VisionStory API 的认证方式，以及数字人视频、声音、语音合成、音频转写、图像和 AI 视频的接入流程。","md",{},{"title":490,"order":121},"概览","\u002Fguides-zh\u002Foverview",{"title":5,"description":486},"guides-zh\u002Foverview","_kIpyDSNZ9dXfHacHpIBoHUmL71-jU5yzelv5-mlQdI","\u003Cpre class=\"shiki github-dark-default\" style=\"background-color:#0d1117;color:#e6edf3\" tabindex=\"0\">\u003Ccode>\u003Cspan class=\"line\">\u003Cspan>X-API-Key: $VISIONSTORY_API_KEY\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan>\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>","\u003Cpre class=\"shiki github-dark-default\" style=\"background-color:#0d1117;color:#e6edf3\" tabindex=\"0\">\u003Ccode>\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">{\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">  \"data\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: {\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">    \"video_id\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"YOUR_VIDEO_ID\"\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">  },\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">  \"message\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"success\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">  \"server_time\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"2026-08-20T06:15:18Z\"\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">}\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>","\u003Cpre class=\"shiki github-dark-default\" style=\"background-color:#0d1117;color:#e6edf3\" tabindex=\"0\">\u003Ccode>\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">curl\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> -s\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> -H\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> \"X-API-Key: \u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">$VISIONSTORY_API_KEY\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Favatars\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>","\u003Cpre class=\"shiki github-dark-default\" style=\"background-color:#0d1117;color:#e6edf3\" tabindex=\"0\">\u003Ccode>\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">curl\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> -s\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> -H\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> \"X-API-Key: \u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">$VISIONSTORY_API_KEY\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Fvoices\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>","\u003Cpre class=\"shiki github-dark-default\" style=\"background-color:#0d1117;color:#e6edf3\" tabindex=\"0\">\u003Ccode>\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">curl\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> -s\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> -H\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> \"X-API-Key: \u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">$VISIONSTORY_API_KEY\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Fbilling\u002Fcredits\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>",1788547143924]