{"openapi":"3.0.3","info":{"title":"VisionDock Receipt, Invoice & Table OCR to JSON/CSV API","version":"3.0.0","description":"Zero-config Multimodal AI Document Parser. Extract structured line-item rows, tax totals, and key-value summaries from crumpled thermal receipts, handwritten tips, B2B vendor invoices, bank statements, business cards, and CJK menus (Japanese/Korean/Chinese) with Neural TTS."},"servers":[{"url":"https://visiondock.ntstudio.online","description":"Cloudflare Global Edge Production"}],"paths":{"/api/ocr":{"post":{"summary":"Extract structured JSON table rows & summary from receipt/invoice/document image","description":"Pass a `base64` image and an optional `preset` (e.g. `receipt-to-excel`, `invoice-ocr-scanner`, `bank-statement-to-csv`, `japanese-manga-ocr`) or custom `prompt`. Returns both raw text and auto-parsed structured JSON (`summary`, `columns`, `rows`).","operationId":"extractDocumentOcr","requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","required":["base64"],"properties":{"base64":{"type":"string","example":"DEMO_SAMPLE","description":"Base64-encoded image string or full data URL (pass 'DEMO_SAMPLE' for instant sandbox test)"},"preset":{"type":"string","enum":["receipt-to-excel","invoice-ocr-scanner","gas-receipt-tax-tracker","bank-statement-to-csv","image-table-to-csv","packing-slip-to-excel","handwriting-to-text","business-card-to-vcard","japanese-manga-ocr","korean-menu-ocr","chinese-ocr-tts","math-screenshot-solver","screenshot-to-code","sql-schema-ocr","medical-bill-ocr","real-estate-lease-ocr"],"default":"receipt-to-excel","description":"Pre-configured domain extraction schema (automatically applies optimized JSON prompt)"},"prompt":{"type":"string","description":"Optional custom extraction instruction (overrides preset prompt if provided)"}}}}}},"responses":{"200":{"description":"Successful multimodal OCR extraction with structured JSON output","content":{"application/json":{"schema":{"type":"object","properties":{"success":{"type":"boolean","example":true},"preset":{"type":"string","example":"receipt-to-excel"},"parsed":{"type":"object","description":"Auto-parsed structured document schema ready for Excel/CSV/ERP ingestion","properties":{"summary":{"type":"object","example":{"Merchant":"Brooklyn Bistro","Date":"2026-10-22","Tax":"$10.38","Total":"$150.00"}},"columns":{"type":"array","items":{"type":"string"},"example":["Qty","Description","Category","Amount"]},"rows":{"type":"array","items":{"type":"array","items":{"type":"string"}},"example":[["2","Wagyu Smash Burger","Meals","$37.00"]]},"notes":{"type":"string"}}},"data":{"type":"object","properties":{"text":{"type":"string"},"provider":{"type":"string","example":"describeimage"},"model":{"type":"string","example":"gemini-2.5-flash-lite"}}}}}}}}}}},"/api/tts":{"get":{"summary":"Synthesize natural Neural TTS audio stream (MP3)","operationId":"synthesizeSpeech","parameters":[{"name":"q","in":"query","required":true,"schema":{"type":"string","example":"いらっしゃいませ！ご注文はお決まりですか？"},"description":"Text to synthesize (up to 300 chars)"},{"name":"tl","in":"query","required":false,"schema":{"type":"string","default":"en","enum":["en","ja","ko","zh-CN","vi","es","fr","de"]},"description":"BCP-47 language code"}],"responses":{"200":{"description":"MP3 audio stream (audio/mpeg)"}}}},"/api/catalog":{"get":{"summary":"List all 16 supported OCR presets and extraction schemas","operationId":"listOcrPresets","responses":{"200":{"description":"Array of 16 specialized document intelligence presets"}}}}}}