[{"data":1,"prerenderedAt":182},["ShallowReactive",2],{"reference-detail-transcribe_audio_api_v1_audio_transcribe_post":3,"developer-code-1qvyx6g":180,"developer-code-w3lmng":181},{"tag":4,"sourceTag":4,"tagSlug":5,"method":6,"path":7,"slug":8,"summary":9,"description":10,"operationId":11,"groupOrder":12,"descriptionHtml":13,"parameters":14,"requestBody":22,"responses":67,"security":167,"codeSamples":170},"Audio","audio","POST","\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe","transcribe-audio","Transcribe audio","Transcribe speech audio to text with word-level timestamps; optionally detect speaker turns\n(`diarize`) or render an SRT subtitle track (`srt`). Billing: 1 credit per started 5 minutes of\naudio, charged only on success. Synchronous — audio up to 30 minutes. Per-key concurrency is\nlimited during beta; requests beyond the limit are rejected, not queued.","transcribe_audio_api_v1_audio_transcribe_post",999,"\u003Cp>Transcribe speech audio to text with word-level timestamps; optionally detect speaker turns (\u003Ccode>diarize\u003C\u002Fcode>) or render an SRT subtitle track (\u003Ccode>srt\u003C\u002Fcode>). Billing: 1 credit per started 5 minutes of audio, charged only on success. Synchronous — audio up to 30 minutes. Per-key concurrency is limited during beta; requests beyond the limit are rejected, not queued.\u003C\u002Fp>",[15],{"name":16,"in":17,"required":18,"description":19,"type":20,"example":21},"X-API-Key","header",true,"Your VisionStory API key (`sk-vs-...`), kept server-side. Create or manage keys in [API keys](\u002Fapi-keys) (Pro plan and up).","string","sk-vs-your-api-key",{"required":18,"contentType":23,"schema":24,"example":64},"application\u002Fjson",{"type":25,"description":26,"nullable":27,"properties":28},"TranscribeRequest","",false,[29,55,60],{"name":5,"required":18,"type":30,"description":31,"nullable":27,"properties":32},"MediaRef","A media reference — provide exactly one of: `asset_id` (from the asset library, reusable across\nrequests), `url` (one-off public URL), or `inline_data` (one-off base64, not stored).",[33,38,51],{"name":34,"required":27,"type":35,"description":36,"nullable":18,"properties":37},"asset_id","string | null","Asset ID from POST \u002Fapi\u002Fv1\u002Fasset; use for materials reused across requests.",[],{"name":39,"required":27,"type":40,"description":41,"nullable":18,"properties":42},"inline_data","InlineDataModel | null","Inline base64 media data for one-off use; not added to your asset library.",[43,47],{"name":44,"required":18,"type":20,"description":45,"nullable":27,"properties":46},"data","The file's raw bytes encoded as a base64 string (no `data:` URI prefix).",[],{"name":48,"required":18,"type":20,"description":49,"nullable":27,"properties":50},"mime_type","MIME type of the inline data, used to detect image vs audio. Audio: ['audio\u002Favi', 'audio\u002Fmpeg', 'audio\u002Fmp3', 'audio\u002Fmp4', 'audio\u002Fm4a', 'audio\u002Fwav']; images: ['image\u002Fjpeg', 'image\u002Fjpg', 'image\u002Fpng', 'image\u002Fwebp', 'image\u002Fheic'].",[],{"name":52,"required":27,"type":35,"description":53,"nullable":18,"properties":54},"url","Publicly accessible media URL for one-off use; not added to your asset library.",[],{"name":56,"required":27,"type":57,"description":58,"nullable":27,"default":27,"properties":59},"diarize","boolean","Set true to detect speaker turns; each word then carries a `speaker` label.",[],{"name":61,"required":27,"type":57,"description":62,"nullable":27,"default":27,"properties":63},"srt","Set true to also return an SRT subtitle rendering of the transcript.",[],{"audio":65,"diarize":18,"srt":18},{"url":66},"https:\u002F\u002Fexample.com\u002Fmedia\u002Finterview.mp3",[68,140],{"status":69,"description":70,"contentType":23,"schema":71,"example":133},"200","Successful Response",{"type":72,"description":26,"nullable":27,"properties":73},"BaseSuccessResponse_TranscribeResponse_",[74,123,128],{"name":44,"required":18,"type":75,"description":76,"nullable":18,"properties":77},"TranscribeResponse | null","The endpoint payload. Its shape is specific to each endpoint (see that endpoint's response schema); null for operations that return no body, such as delete.",[78,84,89,93,96,100],{"name":79,"required":27,"type":80,"description":81,"nullable":27,"default":82,"properties":83},"cost_credit","integer","Credits charged for this request.",0,[],{"name":85,"required":27,"type":86,"description":87,"nullable":27,"default":82,"properties":88},"duration_sec","number","Duration of the input audio in seconds.",[],{"name":90,"required":27,"type":20,"description":91,"nullable":27,"default":26,"properties":92},"language","Detected language code of the audio, e.g. `en`; may be empty.",[],{"name":61,"required":27,"type":20,"description":94,"nullable":27,"default":26,"properties":95},"SRT subtitle text; empty unless `srt: true` was requested.",[],{"name":97,"required":18,"type":20,"description":98,"nullable":27,"properties":99},"text","Full transcript text.",[],{"name":101,"required":27,"type":102,"description":103,"nullable":27,"properties":104,"items":105},"words","WordDto[]","Word-level timestamps.",[],{"type":106,"description":26,"nullable":27,"properties":107},"WordDto",[108,112,116,120],{"name":109,"required":18,"type":86,"description":110,"nullable":27,"properties":111},"end_sec","Word end time in seconds.",[],{"name":113,"required":27,"type":35,"description":114,"nullable":18,"properties":115},"speaker","Speaker label, present only when `diarize` was requested.",[],{"name":117,"required":18,"type":86,"description":118,"nullable":27,"properties":119},"start_sec","Word start time in seconds.",[],{"name":97,"required":18,"type":20,"description":121,"nullable":27,"properties":122},"The word as written.",[],{"name":124,"required":27,"type":20,"description":125,"nullable":27,"default":126,"properties":127},"message","Human-readable status message; `\"success\"` on a successful call.","success",[],{"name":129,"required":18,"type":130,"description":131,"nullable":27,"properties":132},"server_time","string · date-time","Server-side timestamp when the response was produced, in ISO 8601 format (UTC).",[],{"data":134,"server_time":139,"message":126},{"text":135,"cost_credit":82,"duration_sec":82,"language":26,"srt":26,"words":136},"Welcome to VisionStory.",[137],{"end_sec":138,"start_sec":138,"text":135,"speaker":20},1,"2026-08-24T08:00:00Z",{"status":141,"description":142,"contentType":23,"schema":143,"example":165},"default","Error response. All failures share one envelope: an `error` object with a numeric `code`, a human-readable `message`, an optional `details` string, and an optional `hint` giving an actionable next step (useful for AI agents).",{"type":144,"description":26,"nullable":27,"properties":145},"ErrorResponse",[146],{"name":147,"required":18,"type":148,"description":26,"nullable":27,"properties":149},"error","ErrorDetail",[150,154,158,162],{"name":151,"required":18,"type":80,"description":152,"nullable":27,"properties":153},"code","Machine-readable error code. Mirrors the HTTP status for transport-level failures (e.g. 401, 404, 422, 500) and may carry a business-specific code otherwise.",[],{"name":155,"required":27,"type":35,"description":156,"nullable":18,"properties":157},"details","Optional structured detail about the failure, e.g. a JSON string of per-field validation errors on a 422. Absent when there is nothing extra to report.",[],{"name":159,"required":27,"type":35,"description":160,"nullable":18,"properties":161},"hint","Actionable next step for resolving the error, written for both humans and AI agents (e.g. how to fix the request, or where to obtain an API key). May be absent.",[],{"name":124,"required":18,"type":20,"description":163,"nullable":27,"properties":164},"Human-readable explanation of what went wrong. Safe to log or surface to end users; not localized.",[],{"error":166},{"code":138,"message":20,"details":20,"hint":20},[168],{"APIKeyHeader":169},[],[171,174,177],{"lang":172,"source":173},"SDK","from visionstory import VisionStoryClient\n\nclient = VisionStoryClient.from_env()\ntranscript = client.transcribe_audio(\n    audio_url=\"https:\u002F\u002Fexample.com\u002Fmedia\u002Finterview.mp3\",\n    diarize=True,\n    srt=True,\n)\nprint(transcript)",{"lang":175,"source":176},"REST","import os\nimport requests\n\nresponse = requests.post(\n    \"https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe\",\n    headers={\"X-API-Key\": os.environ[\"VISIONSTORY_API_KEY\"]},\n    json={\n      \"audio\": {\n        \"url\": \"https:\u002F\u002Fexample.com\u002Fmedia\u002Finterview.mp3\"\n      },\n      \"diarize\": true,\n      \"srt\": true\n    },\n)\nresponse.raise_for_status()\nprint(response.json())",{"lang":178,"source":179},"cURL","curl --request POST 'https:\u002F\u002Fopenapi.visionstory.ai\u002Fapi\u002Fv1\u002Faudio\u002Ftranscribe' \\\n  --header 'X-API-Key: $VISIONSTORY_API_KEY' \\\n  --header 'Content-Type: application\u002Fjson' \\\n  --data '{\n  \"audio\": {\n    \"url\": \"https:\u002F\u002Fexample.com\u002Fmedia\u002Finterview.mp3\"\n  },\n  \"diarize\": true,\n  \"srt\": true\n}'","\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\"> 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_url\u003C\u002Fspan>\u003Cspan style=\"color:#FF7B72\">=\u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"https:\u002F\u002Fexample.com\u002Fmedia\u002Finterview.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:#79C0FF\">print\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">(transcript)\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\">    \"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\">    \"cost_credit\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">0\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\">0\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\">\"\"\u003C\u002Fspan>\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\">\"\"\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>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">        \"end_sec\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">1\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">,\u003C\u002Fspan>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#7EE787\">        \"start_sec\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#79C0FF\">1\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\">        \"speaker\"\u003C\u002Fspan>\u003Cspan style=\"color:#E6EDF3\">: \u003C\u002Fspan>\u003Cspan style=\"color:#A5D6FF\">\"string\"\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\">\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\">\"2026-08-24T08:00:00Z\"\u003C\u002Fspan>\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>\u003C\u002Fspan>\n\u003Cspan class=\"line\">\u003Cspan style=\"color:#E6EDF3\">}\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fcode>\u003C\u002Fpre>",1788337170753]