[{"data":1,"prerenderedAt":741},["ShallowReactive",2],{"guide-\u002Fguides\u002Faudio-understanding":3,"developer-code-p8h6tt":736,"developer-code-w8ejwf":737,"developer-code-1iqk4u0":738,"developer-code-1s4gqk5":739,"developer-code-edw1yz":740},{"id":4,"title":5,"body":6,"description":727,"extension":728,"meta":729,"navigation":730,"path":732,"seo":733,"stem":734,"__hash__":735},"guides\u002Fguides\u002Faudio-understanding.md","Speech to Text and Alignment API",{"type":7,"value":8,"toc":719},"minimark",[9,19,22,27,80,98,102,119,196,203,371,374,506,510,518,569,592,596,646,657,661,682,686,715],[10,11,12,13,18],"p",{},"The VisionStory Speech to Text API turns speech audio into text, subtitles, and precise word timing. Use transcription when you need speech-to-text, speaker labels, or SRT output. Use alignment when you already know the spoken script and need accurate timestamps for every word. For structured extraction from images, audio, or video, use ",[14,15,17],"a",{"href":16},"\u002Fguides\u002Fmedia-understanding","Media Understanding",".",[10,20,21],{},"Both endpoints are synchronous, accept WAV or MP3 audio up to 15 MB, and charge 1 credit per started 5 minutes only when processing succeeds. An active Pro plan or above is required; no separate beta allowlist is needed.",[23,24,26],"h2",{"id":25},"audio-transcription-and-alignment-endpoints","Audio transcription and alignment endpoints",[28,29,30,46],"table",{},[31,32,33],"thead",{},[34,35,36,40,43],"tr",{},[37,38,39],"th",{},"Method",[37,41,42],{},"Path",[37,44,45],{},"Use it for",[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],{},"Speech-to-text with optional speaker diarization and SRT subtitles",[34,67,68,72,77],{},[52,69,70],{},[55,71,57],{},[52,73,74],{},[55,75,76],{},"\u002Fapi\u002Fv1\u002Faudio\u002Falign",[52,78,79],{},"Word-level timing when the exact spoken text is already known",[10,81,82,83,86,87,90,91,94,95,18],{},"Each request accepts exactly one audio source inside ",[55,84,85],{},"audio",": a reusable ",[55,88,89],{},"asset_id",", a public ",[55,92,93],{},"url",", or base64 ",[55,96,97],{},"inline_data",[23,99,101],{"id":100},"transcribe-audio-to-text","Transcribe audio to text",[10,103,104,105,108,109,112,113,115,116,118],{},"Set ",[55,106,107],{},"diarize: true"," to label speaker turns and ",[55,110,111],{},"srt: true"," to include a ready-to-save subtitle track. The flags are independent: ",[55,114,111],{}," works without ",[55,117,107],{},", and speaker labels are omitted unless you explicitly request diarization.",[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],{},"The response contains the full transcript, detected language, word timestamps, optional ",[55,200,201],{},"speaker"," labels, optional SRT, duration, and credits charged:",[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],{},"With the 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","Align a script with audio",[10,511,512,513,517],{},"Alignment is useful after ",[14,514,516],{"href":515},"\u002Fguides\u002Ftext-to-speech","text-to-speech generation",", dubbing, or voice-over production. Send the exact text spoken in the audio:",[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",[10,570,571,572,273,575,578,579,582,583,273,586,578,589,18],{},"The response returns ",[55,573,574],{},"words",[55,576,577],{},"duration_sec",", and ",[55,580,581],{},"cost_credit",". Each word includes ",[55,584,585],{},"text",[55,587,588],{},"start_sec",[55,590,591],{},"end_sec",[23,593,595],{"id":594},"use-the-cli-or-mcp","Use the CLI or MCP",[120,597,599],{"className":122,"code":598,"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",[55,600,601,627],{"__ignoreMap":125},[129,602,603,606,609,612,615,618,621,624],{"class":131,"line":132},[129,604,605],{"class":135},"visionstory",[129,607,608],{"class":146}," transcribe",[129,610,611],{"class":139}," --audio-file",[129,613,614],{"class":146}," interview.mp3",[129,616,617],{"class":139}," --diarize",[129,619,620],{"class":139}," --srt",[129,622,623],{"class":139}," --output",[129,625,626],{"class":146}," interview.srt\n",[129,628,629,631,634,637,640,643],{"class":131,"line":153},[129,630,605],{"class":135},[129,632,633],{"class":146}," align",[129,635,636],{"class":139}," --audio-url",[129,638,639],{"class":146}," https:\u002F\u002Fexample.com\u002Fspeech.mp3",[129,641,642],{"class":139}," --text",[129,644,645],{"class":146}," \"Welcome to VisionStory.\"\n",[10,647,648,649,652,653,656],{},"MCP clients expose the same workflows as ",[55,650,651],{},"transcribe_audio"," and ",[55,654,655],{},"align_audio",". The local stdio MCP accepts file paths, URLs, or asset IDs. The remote MCP accepts public URLs or reusable asset IDs because it cannot read files from your computer.",[23,658,660],{"id":659},"limits-and-billing","Limits and billing",[662,663,664,668,671,674,677],"ul",{},[665,666,667],"li",{},"Audio input: WAV or MP3, up to 15 MB.",[665,669,670],{},"Processing: synchronous; use short audio where possible to avoid client or proxy timeouts.",[665,672,673],{},"Billing: 1 credit per started 5 minutes, charged only on success.",[665,675,676],{},"Concurrency: requests beyond the per-key synchronous limit are rejected rather than queued.",[665,678,679,680,18],{},"Reuse: upload frequently used audio through the Assets API and pass its ",[55,681,89],{},[23,683,685],{"id":684},"related-visionstory-api-guides","Related VisionStory API guides",[662,687,688,694,701,708],{},[665,689,690,693],{},[14,691,692],{"href":515},"Text to Speech"," — generate MP3 speech, then align it for subtitles.",[665,695,696,700],{},[14,697,699],{"href":698},"\u002Fguides\u002Fvoices","Voices"," — filter public voices or clone a reusable voice.",[665,702,703,707],{},[14,704,706],{"href":705},"\u002Fguides\u002Fsdk","Python SDK"," — call transcription and alignment from Python.",[665,709,710,714],{},[14,711,713],{"href":712},"\u002Freference","API reference"," — exact request and response schemas.",[716,717,718],"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":720},[721,722,723,724,725,726],{"id":25,"depth":153,"text":26},{"id":100,"depth":153,"text":101},{"id":508,"depth":153,"text":509},{"id":594,"depth":153,"text":595},{"id":659,"depth":153,"text":660},{"id":684,"depth":153,"text":685},"Transcribe WAV or MP3 speech to text, get word-level timestamps, identify speakers, generate SRT subtitles, or align a known script with audio using the VisionStory API.","md",{},{"title":731,"order":307},"Speech to Text","\u002Fguides\u002Faudio-understanding",{"title":5,"description":727},"guides\u002Faudio-understanding","DK56kelUUwrFtO43sl1Gu1trKOBlaVs_Lz36sIoGVTU","\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>",1790231923840]