[{"data":1,"prerenderedAt":740},["ShallowReactive",2],{"guide-\u002Fguides-zh\u002Faudio-understanding":3,"developer-code-p8h6tt":735,"developer-code-w8ejwf":736,"developer-code-1iqk4u0":737,"developer-code-1s4gqk5":738,"developer-code-edw1yz":739},{"id":4,"title":5,"body":6,"description":726,"extension":727,"meta":728,"navigation":729,"path":731,"seo":732,"stem":733,"__hash__":734},"guidesZh\u002Fguides-zh\u002Faudio-understanding.md","语音转文字与对齐 API",{"type":7,"value":8,"toc":718},"minimark",[9,19,22,27,80,98,102,119,196,203,371,374,506,510,518,569,593,597,647,657,661,682,686,714],[10,11,12,13,18],"p",{},"VisionStory 语音转文字 API 可将语音音频转换为文本、字幕和精确的词级时间戳。需要识别语音内容、区分说话人或生成 SRT 时，使用转写接口；已经有准确脚本、只需要每个词的时间戳时，使用对齐接口。从图片、音频或视频中提取结构化内容，请使用",[14,15,17],"a",{"href":16},"\u002Fguides\u002Fmedia-understanding","媒体理解","。",[10,20,21],{},"两个接口均同步返回结果，接受不超过 15 MB 的 WAV 或 MP3 音频。每 5 分钟收费 1 点，不足 5 分钟按 5 分钟计算，仅处理成功时收费。需要有效的 Pro 或更高等级订阅，无需额外申请 Beta 白名单。",[23,24,26],"h2",{"id":25},"audio-transcription-and-alignment-endpoints","音频转写与对齐接口",[28,29,30,46],"table",{},[31,32,33],"thead",{},[34,35,36,40,43],"tr",{},[37,38,39],"th",{},"方法",[37,41,42],{},"路径",[37,44,45],{},"适用场景",[47,48,49,66],"tbody",{},[34,50,51,58,63],{},[52,53,54],"td",{},[55,56,57],"code",{},"POST",[52,59,60],{},[55,61,62],{},"\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe",[52,64,65],{},"语音转文字，可选说话人分离和 SRT 字幕",[34,67,68,72,77],{},[52,69,70],{},[55,71,57],{},[52,73,74],{},[55,75,76],{},"\u002Fapi\u002Fv1\u002Faudio\u002Falign",[52,78,79],{},"已知准确脚本时，获取词级时间戳",[10,81,82,83,86,87,90,91,94,95,18],{},"每次请求都必须在 ",[55,84,85],{},"audio"," 中选择且仅选择一种音频来源：可复用的 ",[55,88,89],{},"asset_id","、可公开访问的 ",[55,92,93],{},"url","，或包含 Base64 数据的 ",[55,96,97],{},"inline_data",[23,99,101],{"id":100},"transcribe-audio-to-text","将音频转写为文本",[10,103,104,105,108,109,112,113,115,116,118],{},"设置 ",[55,106,107],{},"diarize: true"," 可标记不同说话人的发言，设置 ",[55,110,111],{},"srt: true"," 可返回可直接保存的字幕内容。两者独立：使用 ",[55,114,111],{}," 不需要同时开启 ",[55,117,107],{},"；只有明确请求说话人分离时，响应才包含说话人标签。",[120,121,126],"pre",{"className":122,"code":123,"language":124,"meta":125,"style":125},"language-bash shiki shiki-themes github-light github-dark","curl -s -X POST \\\n  -H \"X-API-Key: $VISIONSTORY_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"audio\":{\"url\":\"https:\u002F\u002Fexample.com\u002Finterview.mp3\"},\"diarize\":true,\"srt\":true}' \\\n  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe\n","bash","",[55,127,128,151,169,179,190],{"__ignoreMap":125},[129,130,133,137,141,144,148],"span",{"class":131,"line":132},"line",1,[129,134,136],{"class":135},"sScJk","curl",[129,138,140],{"class":139},"sj4cs"," -s",[129,142,143],{"class":139}," -X",[129,145,147],{"class":146},"sZZnC"," POST",[129,149,150],{"class":139}," \\\n",[129,152,154,157,160,164,167],{"class":131,"line":153},2,[129,155,156],{"class":139},"  -H",[129,158,159],{"class":146}," \"X-API-Key: ",[129,161,163],{"class":162},"sVt8B","$VISIONSTORY_API_KEY",[129,165,166],{"class":146},"\"",[129,168,150],{"class":139},[129,170,172,174,177],{"class":131,"line":171},3,[129,173,156],{"class":139},[129,175,176],{"class":146}," \"Content-Type: application\u002Fjson\"",[129,178,150],{"class":139},[129,180,182,185,188],{"class":131,"line":181},4,[129,183,184],{"class":139},"  -d",[129,186,187],{"class":146}," '{\"audio\":{\"url\":\"https:\u002F\u002Fexample.com\u002Finterview.mp3\"},\"diarize\":true,\"srt\":true}'",[129,189,150],{"class":139},[129,191,193],{"class":131,"line":192},5,[129,194,195],{"class":146},"  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe\n",[10,197,198,199,202],{},"响应包含完整转写文本、识别出的语言、词级时间戳、可选的 ",[55,200,201],{},"speaker"," 标签、可选 SRT、音频时长和消耗的点数：",[120,204,208],{"className":205,"code":206,"language":207,"meta":125,"style":125},"language-json shiki shiki-themes github-light github-dark","{\n  \"data\": {\n    \"text\": \"Welcome to VisionStory.\",\n    \"language\": \"en\",\n    \"words\": [\n      { \"text\": \"Welcome\", \"start_sec\": 0.0, \"end_sec\": 0.48, \"speaker\": \"speaker_0\" }\n    ],\n    \"srt\": \"1\\n00:00:00,000 --> 00:00:01,200\\nWelcome to VisionStory.\",\n    \"duration_sec\": 1.2,\n    \"cost_credit\": 1\n  }\n}\n","json",[55,209,210,215,223,237,249,257,305,311,335,348,359,365],{"__ignoreMap":125},[129,211,212],{"class":131,"line":132},[129,213,214],{"class":162},"{\n",[129,216,217,220],{"class":131,"line":153},[129,218,219],{"class":139},"  \"data\"",[129,221,222],{"class":162},": {\n",[129,224,225,228,231,234],{"class":131,"line":171},[129,226,227],{"class":139},"    \"text\"",[129,229,230],{"class":162},": ",[129,232,233],{"class":146},"\"Welcome to VisionStory.\"",[129,235,236],{"class":162},",\n",[129,238,239,242,244,247],{"class":131,"line":181},[129,240,241],{"class":139},"    \"language\"",[129,243,230],{"class":162},[129,245,246],{"class":146},"\"en\"",[129,248,236],{"class":162},[129,250,251,254],{"class":131,"line":192},[129,252,253],{"class":139},"    \"words\"",[129,255,256],{"class":162},": [\n",[129,258,260,263,266,268,271,274,277,279,282,284,287,289,292,294,297,299,302],{"class":131,"line":259},6,[129,261,262],{"class":162},"      { ",[129,264,265],{"class":139},"\"text\"",[129,267,230],{"class":162},[129,269,270],{"class":146},"\"Welcome\"",[129,272,273],{"class":162},", ",[129,275,276],{"class":139},"\"start_sec\"",[129,278,230],{"class":162},[129,280,281],{"class":139},"0.0",[129,283,273],{"class":162},[129,285,286],{"class":139},"\"end_sec\"",[129,288,230],{"class":162},[129,290,291],{"class":139},"0.48",[129,293,273],{"class":162},[129,295,296],{"class":139},"\"speaker\"",[129,298,230],{"class":162},[129,300,301],{"class":146},"\"speaker_0\"",[129,303,304],{"class":162}," }\n",[129,306,308],{"class":131,"line":307},7,[129,309,310],{"class":162},"    ],\n",[129,312,314,317,319,322,325,328,330,333],{"class":131,"line":313},8,[129,315,316],{"class":139},"    \"srt\"",[129,318,230],{"class":162},[129,320,321],{"class":146},"\"1",[129,323,324],{"class":139},"\\n",[129,326,327],{"class":146},"00:00:00,000 --> 00:00:01,200",[129,329,324],{"class":139},[129,331,332],{"class":146},"Welcome to VisionStory.\"",[129,334,236],{"class":162},[129,336,338,341,343,346],{"class":131,"line":337},9,[129,339,340],{"class":139},"    \"duration_sec\"",[129,342,230],{"class":162},[129,344,345],{"class":139},"1.2",[129,347,236],{"class":162},[129,349,351,354,356],{"class":131,"line":350},10,[129,352,353],{"class":139},"    \"cost_credit\"",[129,355,230],{"class":162},[129,357,358],{"class":139},"1\n",[129,360,362],{"class":131,"line":361},11,[129,363,364],{"class":162},"  }\n",[129,366,368],{"class":131,"line":367},12,[129,369,370],{"class":162},"}\n",[10,372,373],{},"使用 Python SDK：",[120,375,379],{"className":376,"code":377,"language":378,"meta":125,"style":125},"language-python shiki shiki-themes github-light github-dark","from pathlib import Path\nfrom visionstory import VisionStoryClient\n\nclient = VisionStoryClient.from_env()\ntranscript = client.transcribe_audio(\n    audio_file=Path(\"interview.mp3\"),\n    diarize=True,\n    srt=True,\n)\nPath(\"interview.srt\").write_text(transcript[\"srt\"], encoding=\"utf-8\")\n","python",[55,380,381,396,408,414,425,435,452,464,475,480],{"__ignoreMap":125},[129,382,383,387,390,393],{"class":131,"line":132},[129,384,386],{"class":385},"szBVR","from",[129,388,389],{"class":162}," pathlib ",[129,391,392],{"class":385},"import",[129,394,395],{"class":162}," Path\n",[129,397,398,400,403,405],{"class":131,"line":153},[129,399,386],{"class":385},[129,401,402],{"class":162}," visionstory ",[129,404,392],{"class":385},[129,406,407],{"class":162}," VisionStoryClient\n",[129,409,410],{"class":131,"line":171},[129,411,413],{"emptyLinePlaceholder":412},true,"\n",[129,415,416,419,422],{"class":131,"line":181},[129,417,418],{"class":162},"client ",[129,420,421],{"class":385},"=",[129,423,424],{"class":162}," VisionStoryClient.from_env()\n",[129,426,427,430,432],{"class":131,"line":192},[129,428,429],{"class":162},"transcript ",[129,431,421],{"class":385},[129,433,434],{"class":162}," client.transcribe_audio(\n",[129,436,437,441,443,446,449],{"class":131,"line":259},[129,438,440],{"class":439},"s4XuR","    audio_file",[129,442,421],{"class":385},[129,444,445],{"class":162},"Path(",[129,447,448],{"class":146},"\"interview.mp3\"",[129,450,451],{"class":162},"),\n",[129,453,454,457,459,462],{"class":131,"line":307},[129,455,456],{"class":439},"    diarize",[129,458,421],{"class":385},[129,460,461],{"class":139},"True",[129,463,236],{"class":162},[129,465,466,469,471,473],{"class":131,"line":313},[129,467,468],{"class":439},"    srt",[129,470,421],{"class":385},[129,472,461],{"class":139},[129,474,236],{"class":162},[129,476,477],{"class":131,"line":337},[129,478,479],{"class":162},")\n",[129,481,482,484,487,490,493,496,499,501,504],{"class":131,"line":350},[129,483,445],{"class":162},[129,485,486],{"class":146},"\"interview.srt\"",[129,488,489],{"class":162},").write_text(transcript[",[129,491,492],{"class":146},"\"srt\"",[129,494,495],{"class":162},"], ",[129,497,498],{"class":439},"encoding",[129,500,421],{"class":385},[129,502,503],{"class":146},"\"utf-8\"",[129,505,479],{"class":162},[23,507,509],{"id":508},"align-a-script-with-audio","将脚本与音频对齐",[10,511,512,513,517],{},"对齐适用于",[14,514,516],{"href":515},"\u002Fguides\u002Ftext-to-speech","文本转语音","、配音或旁白制作之后。请提交与音频中实际说出的内容完全一致的文本：",[120,519,521],{"className":122,"code":520,"language":124,"meta":125,"style":125},"curl -s -X POST \\\n  -H \"X-API-Key: $VISIONSTORY_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"audio\":{\"asset_id\":\"YOUR_AUDIO_ASSET_ID\"},\"text\":\"Welcome to VisionStory.\"}' \\\n  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Falign\n",[55,522,523,535,547,555,564],{"__ignoreMap":125},[129,524,525,527,529,531,533],{"class":131,"line":132},[129,526,136],{"class":135},[129,528,140],{"class":139},[129,530,143],{"class":139},[129,532,147],{"class":146},[129,534,150],{"class":139},[129,536,537,539,541,543,545],{"class":131,"line":153},[129,538,156],{"class":139},[129,540,159],{"class":146},[129,542,163],{"class":162},[129,544,166],{"class":146},[129,546,150],{"class":139},[129,548,549,551,553],{"class":131,"line":171},[129,550,156],{"class":139},[129,552,176],{"class":146},[129,554,150],{"class":139},[129,556,557,559,562],{"class":131,"line":181},[129,558,184],{"class":139},[129,560,561],{"class":146}," '{\"audio\":{\"asset_id\":\"YOUR_AUDIO_ASSET_ID\"},\"text\":\"Welcome to VisionStory.\"}'",[129,563,150],{"class":139},[129,565,566],{"class":131,"line":192},[129,567,568],{"class":146},"  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Falign\n",[10,570,571,572,575,576,579,580,583,584,575,587,579,590,18],{},"响应返回 ",[55,573,574],{},"words","、",[55,577,578],{},"duration_sec"," 和 ",[55,581,582],{},"cost_credit","。每个词包含 ",[55,585,586],{},"text",[55,588,589],{},"start_sec",[55,591,592],{},"end_sec",[23,594,596],{"id":595},"use-the-cli-or-mcp","使用 CLI 或 MCP",[120,598,600],{"className":122,"code":599,"language":124,"meta":125,"style":125},"visionstory transcribe --audio-file interview.mp3 --diarize --srt --output interview.srt\nvisionstory align --audio-url https:\u002F\u002Fexample.com\u002Fspeech.mp3 --text \"Welcome to VisionStory.\"\n",[55,601,602,628],{"__ignoreMap":125},[129,603,604,607,610,613,616,619,622,625],{"class":131,"line":132},[129,605,606],{"class":135},"visionstory",[129,608,609],{"class":146}," transcribe",[129,611,612],{"class":139}," --audio-file",[129,614,615],{"class":146}," interview.mp3",[129,617,618],{"class":139}," --diarize",[129,620,621],{"class":139}," --srt",[129,623,624],{"class":139}," --output",[129,626,627],{"class":146}," interview.srt\n",[129,629,630,632,635,638,641,644],{"class":131,"line":153},[129,631,606],{"class":135},[129,633,634],{"class":146}," align",[129,636,637],{"class":139}," --audio-url",[129,639,640],{"class":146}," https:\u002F\u002Fexample.com\u002Fspeech.mp3",[129,642,643],{"class":139}," --text",[129,645,646],{"class":146}," \"Welcome to VisionStory.\"\n",[10,648,649,650,579,653,656],{},"MCP 通过 ",[55,651,652],{},"transcribe_audio",[55,654,655],{},"align_audio"," 提供相同能力。本地 stdio MCP 支持文件路径、URL 或素材 ID；远程 MCP 无法读取你电脑上的文件，因此仅支持可公开访问的 URL 或可复用的素材 ID。",[23,658,660],{"id":659},"limits-and-billing","限制与计费",[662,663,664,668,671,674,677],"ul",{},[665,666,667],"li",{},"音频输入：WAV 或 MP3，文件不超过 15 MB。",[665,669,670],{},"处理方式：同步返回；尽量使用较短音频，避免客户端或代理超时。",[665,672,673],{},"计费：每 5 分钟 1 点，不足 5 分钟按 5 分钟计算，仅成功时收费。",[665,675,676],{},"并发：超出每个 API Key 同步并发上限的请求会被拒绝，不会排队。",[665,678,679,680,18],{},"复用：通过素材 API 上传经常使用的音频，再传入其 ",[55,681,89],{},[23,683,685],{"id":684},"related-visionstory-api-guides","相关 VisionStory API 指南",[662,687,688,693,700,707],{},[665,689,690,692],{},[14,691,516],{"href":515}," — 生成 MP3 语音，再对齐生成字幕。",[665,694,695,699],{},[14,696,698],{"href":697},"\u002Fguides\u002Fvoices","声音"," — 筛选公共声音或克隆可复用的声音。",[665,701,702,706],{},[14,703,705],{"href":704},"\u002Fguides\u002Fsdk","Python SDK"," — 在 Python 中调用转写与对齐。",[665,708,709,713],{},[14,710,712],{"href":711},"\u002Freference","API 参考"," — 查看准确的请求和响应结构。",[715,716,717],"style",{},"html pre.shiki code .sScJk, html code.shiki .sScJk{--shiki-default:#6F42C1;--shiki-dark:#B392F0}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 pre.shiki code .sVt8B, html code.shiki .sVt8B{--shiki-default:#24292E;--shiki-dark:#E1E4E8}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 .szBVR, html code.shiki .szBVR{--shiki-default:#D73A49;--shiki-dark:#F97583}html pre.shiki code .s4XuR, html code.shiki .s4XuR{--shiki-default:#E36209;--shiki-dark:#FFAB70}",{"title":125,"searchDepth":153,"depth":153,"links":719},[720,721,722,723,724,725],{"id":25,"depth":153,"text":26},{"id":100,"depth":153,"text":101},{"id":508,"depth":153,"text":509},{"id":595,"depth":153,"text":596},{"id":659,"depth":153,"text":660},{"id":684,"depth":153,"text":685},"使用 VisionStory API 将 WAV 或 MP3 语音转写为文本，获取词级时间戳、说话人标签和 SRT 字幕，或将已知脚本与音频对齐。","md",{},{"title":730,"order":307},"语音转文字","\u002Fguides-zh\u002Faudio-understanding",{"title":5,"description":726},"guides-zh\u002Faudio-understanding","3x4lB538VrjnkmXEC22ia52c9uGxTfLLX38jbb-XMIw","\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\"> -X\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> POST\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\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:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#79C0FF\">  -H\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> \"Content-Type: application\u002Fjson\"\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#79C0FF\">  -d\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> '{\"audio\":{\"url\":\"https:\u002F\u002Fexample.com\u002Finterview.mp3\"},\"diarize\":true,\"srt\":true}'\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#A5D6FF\">  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe\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:#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\">    \"text\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"Welcome to VisionStory.\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">    \"language\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"en\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">    \"words\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: [\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">      { \u003C\u002Fspan>\u003Cspan style=\"color:#7EE787\">\"text\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"Welcome\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">, \u003C\u002Fspan>\u003Cspan style=\"color:#7EE787\">\"start_sec\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">0.0\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">, \u003C\u002Fspan>\u003Cspan style=\"color:#7EE787\">\"end_sec\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">0.48\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">, \u003C\u002Fspan>\u003Cspan style=\"color:#7EE787\">\"speaker\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"speaker_0\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> }\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">    ],\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">    \"srt\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"1\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">\\n\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">00:00:00,000 --> 00:00:01,200\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">\\n\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">Welcome to VisionStory.\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">    \"duration_sec\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">1.2\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">    \"cost_credit\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">1\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">  }\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:#FF7B72\">from\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> pathlib \u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">import\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> Path\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#FF7B72\">from\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> visionstory \u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">import\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> VisionStoryClient\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">client \u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> VisionStoryClient.from_env()\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">transcript \u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\"> client.transcribe_audio(\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">    audio_file\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">Path(\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"interview.mp3\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">),\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">    diarize\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">True\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">    srt\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">True\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">)\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">Path(\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"interview.srt\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">).write_text(transcript[\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"srt\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">], \u003C\u002Fspan>\u003Cspan style=\"color:#FFA657\">encoding\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"utf-8\"\u003C\u002Fspan>\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\"> -X\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> POST\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\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:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#79C0FF\">  -H\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> \"Content-Type: application\u002Fjson\"\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#79C0FF\">  -d\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> '{\"audio\":{\"asset_id\":\"YOUR_AUDIO_ASSET_ID\"},\"text\":\"Welcome to VisionStory.\"}'\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\"> \\\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#A5D6FF\">  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Falign\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\">visionstory\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> transcribe\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> --audio-file\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> interview.mp3\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> --diarize\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> --srt\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> --output\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> interview.srt\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#FFA657\">visionstory\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> align\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> --audio-url\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> https:\u002F\u002Fexample.com\u002Fspeech.mp3\u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\"> --text\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\"> \"Welcome to VisionStory.\"\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>",1788547143927]