[{"data":1,"prerenderedAt":731},["ShallowReactive",2],{"guide-\u002Fguides\u002Faudio-understanding":3,"developer-code-p8h6tt":726,"developer-code-w8ejwf":727,"developer-code-1iqk4u0":728,"developer-code-1s4gqk5":729,"developer-code-edw1yz":730},{"id":4,"title":5,"body":6,"description":717,"extension":718,"meta":719,"navigation":720,"path":722,"seo":723,"stem":724,"__hash__":725},"guides\u002Fguides\u002Faudio-understanding.md","Audio Transcription and Alignment API",{"type":7,"value":8,"toc":709},"minimark",[9,13,16,21,74,93,97,108,185,192,360,363,495,499,508,559,582,586,636,647,651,672,676,705],[10,11,12],"p",{},"The VisionStory Audio Understanding 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.",[10,14,15],{},"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.",[17,18,20],"h2",{"id":19},"audio-transcription-and-alignment-endpoints","Audio transcription and alignment endpoints",[22,23,24,40],"table",{},[25,26,27],"thead",{},[28,29,30,34,37],"tr",{},[31,32,33],"th",{},"Method",[31,35,36],{},"Path",[31,38,39],{},"Use it for",[41,42,43,60],"tbody",{},[28,44,45,52,57],{},[46,47,48],"td",{},[49,50,51],"code",{},"POST",[46,53,54],{},[49,55,56],{},"\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe",[46,58,59],{},"Speech-to-text with optional speaker diarization and SRT subtitles",[28,61,62,66,71],{},[46,63,64],{},[49,65,51],{},[46,67,68],{},[49,69,70],{},"\u002Fapi\u002Fv1\u002Faudio\u002Falign",[46,72,73],{},"Word-level timing when the exact spoken text is already known",[10,75,76,77,80,81,84,85,88,89,92],{},"Each request accepts exactly one audio source inside ",[49,78,79],{},"audio",": a reusable ",[49,82,83],{},"asset_id",", a public ",[49,86,87],{},"url",", or base64 ",[49,90,91],{},"inline_data",".",[17,94,96],{"id":95},"transcribe-audio-to-text","Transcribe audio to text",[10,98,99,100,103,104,107],{},"Set ",[49,101,102],{},"diarize: true"," to label speaker turns and ",[49,105,106],{},"srt: true"," to include a ready-to-save subtitle track:",[109,110,115],"pre",{"className":111,"code":112,"language":113,"meta":114,"style":114},"language-bash shiki shiki-themes github-light github-dark","curl -s -X POST \\\n  -H \"X-API-Key: $VISIONSTORY_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"audio\":{\"url\":\"https:\u002F\u002Fexample.com\u002Finterview.mp3\"},\"diarize\":true,\"srt\":true}' \\\n  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe\n","bash","",[49,116,117,140,158,168,179],{"__ignoreMap":114},[118,119,122,126,130,133,137],"span",{"class":120,"line":121},"line",1,[118,123,125],{"class":124},"sScJk","curl",[118,127,129],{"class":128},"sj4cs"," -s",[118,131,132],{"class":128}," -X",[118,134,136],{"class":135},"sZZnC"," POST",[118,138,139],{"class":128}," \\\n",[118,141,143,146,149,153,156],{"class":120,"line":142},2,[118,144,145],{"class":128},"  -H",[118,147,148],{"class":135}," \"X-API-Key: ",[118,150,152],{"class":151},"sVt8B","$VISIONSTORY_API_KEY",[118,154,155],{"class":135},"\"",[118,157,139],{"class":128},[118,159,161,163,166],{"class":120,"line":160},3,[118,162,145],{"class":128},[118,164,165],{"class":135}," \"Content-Type: application\u002Fjson\"",[118,167,139],{"class":128},[118,169,171,174,177],{"class":120,"line":170},4,[118,172,173],{"class":128},"  -d",[118,175,176],{"class":135}," '{\"audio\":{\"url\":\"https:\u002F\u002Fexample.com\u002Finterview.mp3\"},\"diarize\":true,\"srt\":true}'",[118,178,139],{"class":128},[118,180,182],{"class":120,"line":181},5,[118,183,184],{"class":135},"  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe\n",[10,186,187,188,191],{},"The response contains the full transcript, detected language, word timestamps, optional ",[49,189,190],{},"speaker"," labels, optional SRT, duration, and credits charged:",[109,193,197],{"className":194,"code":195,"language":196,"meta":114,"style":114},"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",[49,198,199,204,212,226,238,246,294,300,324,337,348,354],{"__ignoreMap":114},[118,200,201],{"class":120,"line":121},[118,202,203],{"class":151},"{\n",[118,205,206,209],{"class":120,"line":142},[118,207,208],{"class":128},"  \"data\"",[118,210,211],{"class":151},": {\n",[118,213,214,217,220,223],{"class":120,"line":160},[118,215,216],{"class":128},"    \"text\"",[118,218,219],{"class":151},": ",[118,221,222],{"class":135},"\"Welcome to VisionStory.\"",[118,224,225],{"class":151},",\n",[118,227,228,231,233,236],{"class":120,"line":170},[118,229,230],{"class":128},"    \"language\"",[118,232,219],{"class":151},[118,234,235],{"class":135},"\"en\"",[118,237,225],{"class":151},[118,239,240,243],{"class":120,"line":181},[118,241,242],{"class":128},"    \"words\"",[118,244,245],{"class":151},": [\n",[118,247,249,252,255,257,260,263,266,268,271,273,276,278,281,283,286,288,291],{"class":120,"line":248},6,[118,250,251],{"class":151},"      { ",[118,253,254],{"class":128},"\"text\"",[118,256,219],{"class":151},[118,258,259],{"class":135},"\"Welcome\"",[118,261,262],{"class":151},", ",[118,264,265],{"class":128},"\"start_sec\"",[118,267,219],{"class":151},[118,269,270],{"class":128},"0.0",[118,272,262],{"class":151},[118,274,275],{"class":128},"\"end_sec\"",[118,277,219],{"class":151},[118,279,280],{"class":128},"0.48",[118,282,262],{"class":151},[118,284,285],{"class":128},"\"speaker\"",[118,287,219],{"class":151},[118,289,290],{"class":135},"\"speaker_0\"",[118,292,293],{"class":151}," }\n",[118,295,297],{"class":120,"line":296},7,[118,298,299],{"class":151},"    ],\n",[118,301,303,306,308,311,314,317,319,322],{"class":120,"line":302},8,[118,304,305],{"class":128},"    \"srt\"",[118,307,219],{"class":151},[118,309,310],{"class":135},"\"1",[118,312,313],{"class":128},"\\n",[118,315,316],{"class":135},"00:00:00,000 --> 00:00:01,200",[118,318,313],{"class":128},[118,320,321],{"class":135},"Welcome to VisionStory.\"",[118,323,225],{"class":151},[118,325,327,330,332,335],{"class":120,"line":326},9,[118,328,329],{"class":128},"    \"duration_sec\"",[118,331,219],{"class":151},[118,333,334],{"class":128},"1.2",[118,336,225],{"class":151},[118,338,340,343,345],{"class":120,"line":339},10,[118,341,342],{"class":128},"    \"cost_credit\"",[118,344,219],{"class":151},[118,346,347],{"class":128},"1\n",[118,349,351],{"class":120,"line":350},11,[118,352,353],{"class":151},"  }\n",[118,355,357],{"class":120,"line":356},12,[118,358,359],{"class":151},"}\n",[10,361,362],{},"With the Python SDK:",[109,364,368],{"className":365,"code":366,"language":367,"meta":114,"style":114},"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",[49,369,370,385,397,403,414,424,441,453,464,469],{"__ignoreMap":114},[118,371,372,376,379,382],{"class":120,"line":121},[118,373,375],{"class":374},"szBVR","from",[118,377,378],{"class":151}," pathlib ",[118,380,381],{"class":374},"import",[118,383,384],{"class":151}," Path\n",[118,386,387,389,392,394],{"class":120,"line":142},[118,388,375],{"class":374},[118,390,391],{"class":151}," visionstory ",[118,393,381],{"class":374},[118,395,396],{"class":151}," VisionStoryClient\n",[118,398,399],{"class":120,"line":160},[118,400,402],{"emptyLinePlaceholder":401},true,"\n",[118,404,405,408,411],{"class":120,"line":170},[118,406,407],{"class":151},"client ",[118,409,410],{"class":374},"=",[118,412,413],{"class":151}," VisionStoryClient.from_env()\n",[118,415,416,419,421],{"class":120,"line":181},[118,417,418],{"class":151},"transcript ",[118,420,410],{"class":374},[118,422,423],{"class":151}," client.transcribe_audio(\n",[118,425,426,430,432,435,438],{"class":120,"line":248},[118,427,429],{"class":428},"s4XuR","    audio_file",[118,431,410],{"class":374},[118,433,434],{"class":151},"Path(",[118,436,437],{"class":135},"\"interview.mp3\"",[118,439,440],{"class":151},"),\n",[118,442,443,446,448,451],{"class":120,"line":296},[118,444,445],{"class":428},"    diarize",[118,447,410],{"class":374},[118,449,450],{"class":128},"True",[118,452,225],{"class":151},[118,454,455,458,460,462],{"class":120,"line":302},[118,456,457],{"class":428},"    srt",[118,459,410],{"class":374},[118,461,450],{"class":128},[118,463,225],{"class":151},[118,465,466],{"class":120,"line":326},[118,467,468],{"class":151},")\n",[118,470,471,473,476,479,482,485,488,490,493],{"class":120,"line":339},[118,472,434],{"class":151},[118,474,475],{"class":135},"\"interview.srt\"",[118,477,478],{"class":151},").write_text(transcript[",[118,480,481],{"class":135},"\"srt\"",[118,483,484],{"class":151},"], ",[118,486,487],{"class":428},"encoding",[118,489,410],{"class":374},[118,491,492],{"class":135},"\"utf-8\"",[118,494,468],{"class":151},[17,496,498],{"id":497},"align-a-script-with-audio","Align a script with audio",[10,500,501,502,507],{},"Alignment is useful after ",[503,504,506],"a",{"href":505},"\u002Fguides\u002Ftext-to-speech","text-to-speech generation",", dubbing, or voice-over production. Send the exact text spoken in the audio:",[109,509,511],{"className":111,"code":510,"language":113,"meta":114,"style":114},"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",[49,512,513,525,537,545,554],{"__ignoreMap":114},[118,514,515,517,519,521,523],{"class":120,"line":121},[118,516,125],{"class":124},[118,518,129],{"class":128},[118,520,132],{"class":128},[118,522,136],{"class":135},[118,524,139],{"class":128},[118,526,527,529,531,533,535],{"class":120,"line":142},[118,528,145],{"class":128},[118,530,148],{"class":135},[118,532,152],{"class":151},[118,534,155],{"class":135},[118,536,139],{"class":128},[118,538,539,541,543],{"class":120,"line":160},[118,540,145],{"class":128},[118,542,165],{"class":135},[118,544,139],{"class":128},[118,546,547,549,552],{"class":120,"line":170},[118,548,173],{"class":128},[118,550,551],{"class":135}," '{\"audio\":{\"asset_id\":\"YOUR_AUDIO_ASSET_ID\"},\"text\":\"Welcome to VisionStory.\"}'",[118,553,139],{"class":128},[118,555,556],{"class":120,"line":181},[118,557,558],{"class":135},"  https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Falign\n",[10,560,561,562,262,565,568,569,572,573,262,576,568,579,92],{},"The response returns ",[49,563,564],{},"words",[49,566,567],{},"duration_sec",", and ",[49,570,571],{},"cost_credit",". Each word includes ",[49,574,575],{},"text",[49,577,578],{},"start_sec",[49,580,581],{},"end_sec",[17,583,585],{"id":584},"use-the-cli-or-mcp","Use the CLI or MCP",[109,587,589],{"className":111,"code":588,"language":113,"meta":114,"style":114},"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",[49,590,591,617],{"__ignoreMap":114},[118,592,593,596,599,602,605,608,611,614],{"class":120,"line":121},[118,594,595],{"class":124},"visionstory",[118,597,598],{"class":135}," transcribe",[118,600,601],{"class":128}," --audio-file",[118,603,604],{"class":135}," interview.mp3",[118,606,607],{"class":128}," --diarize",[118,609,610],{"class":128}," --srt",[118,612,613],{"class":128}," --output",[118,615,616],{"class":135}," interview.srt\n",[118,618,619,621,624,627,630,633],{"class":120,"line":142},[118,620,595],{"class":124},[118,622,623],{"class":135}," align",[118,625,626],{"class":128}," --audio-url",[118,628,629],{"class":135}," https:\u002F\u002Fexample.com\u002Fspeech.mp3",[118,631,632],{"class":128}," --text",[118,634,635],{"class":135}," \"Welcome to VisionStory.\"\n",[10,637,638,639,642,643,646],{},"MCP clients expose the same workflows as ",[49,640,641],{},"transcribe_audio"," and ",[49,644,645],{},"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.",[17,648,650],{"id":649},"limits-and-billing","Limits and billing",[652,653,654,658,661,664,667],"ul",{},[655,656,657],"li",{},"Audio input: WAV or MP3, up to 15 MB.",[655,659,660],{},"Processing: synchronous; use short audio where possible to avoid client or proxy timeouts.",[655,662,663],{},"Billing: 1 credit per started 5 minutes, charged only on success.",[655,665,666],{},"Concurrency: requests beyond the per-key synchronous limit are rejected rather than queued.",[655,668,669,670,92],{},"Reuse: upload frequently used audio through the Assets API and pass its ",[49,671,83],{},[17,673,675],{"id":674},"related-visionstory-api-guides","Related VisionStory API guides",[652,677,678,684,691,698],{},[655,679,680,683],{},[503,681,682],{"href":505},"Text to Speech"," — generate MP3 speech, then align it for subtitles.",[655,685,686,690],{},[503,687,689],{"href":688},"\u002Fguides\u002Fvoices","Voices"," — filter public voices or clone a reusable voice.",[655,692,693,697],{},[503,694,696],{"href":695},"\u002Fguides\u002Fsdk","Python SDK"," — call transcription and alignment from Python.",[655,699,700,704],{},[503,701,703],{"href":702},"\u002Freference","API reference"," — exact request and response schemas.",[706,707,708],"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":114,"searchDepth":142,"depth":142,"links":710},[711,712,713,714,715,716],{"id":19,"depth":142,"text":20},{"id":95,"depth":142,"text":96},{"id":497,"depth":142,"text":498},{"id":584,"depth":142,"text":585},{"id":649,"depth":142,"text":650},{"id":674,"depth":142,"text":675},"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":721,"order":296},"Audio Understanding","\u002Fguides\u002Faudio-understanding",{"title":5,"description":717},"guides\u002Faudio-understanding","fdR3TT22PLjWBuhC4PtD4bK6kLBRjLH_eT_uX4DEsTM","\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>",1788337171220]