{ "openapi": "3.0.1", "info": { "title": "Video OCR - Extract On-Screen Text from Video (Captions)", "description": "Video OCR extracts text from video files - burned-in subtitles, captions, ad hook text, titles, lower-thirds, slide text - as timed segments with frame images, a transcript and an SRT/VTT track. Chains with Video Frame Extractor. $2 per 1,000 frames with text; frames without text are free.", "version": "1.0", "x-build-id": "ajDCxBkfuDYCDOalG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kantolabs~video-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kantolabs-video-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kantolabs~video-ocr/runs": { "post": { "operationId": "runs-sync-kantolabs-video-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kantolabs~video-ocr/run-sync": { "post": { "operationId": "run-sync-kantolabs-video-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "videoUrls": { "title": "Video URLs", "type": "array", "description": "Direct links to video files (MP4, MOV, WEBM, MKV, AVI, M4V, MPEG-TS...), one per line: your own storage, S3/R2/GCS, CDNs, an Apify key-value store, Dropbox or Google Drive share links ('anyone with the link'). Pages of video platforms (YouTube, TikTok, Instagram, Vimeo...) are refused. Leave the sample in place only if you want it read.", "default": [ "https://api.apify.com/v2/key-value-stores/aXcXwfChlioPWAUJv/records/sample-ocr-captions.mp4?signature=ImU3YcEhw0ddoYvT7QD5" ], "items": { "type": "string" } }, "sampleIntervalSeconds": { "title": "Read a frame every (seconds)", "minimum": 0.25, "maximum": 60, "type": "number", "description": "How often a frame is read. 1 s catches every subtitle and caption; 0.5 s suits fast word-by-word TikTok captions; 2-5 s is cheaper for slides, screen recordings and long videos. Frames identical to the previous one are skipped for free.", "default": 1 }, "ocrLanguage": { "title": "Text language (script)", "enum": [ "en", "latin", "cyrillic", "korean", "arabic", "devanagari", "greek", "thai" ], "type": "string", "description": "Script of the on-screen text. `en` also reads Chinese and Japanese. Use `latin` for French, German, Spanish, Portuguese, Czech, Polish and other accented Latin languages, `cyrillic` for Russian, Ukrainian, Bulgarian.", "default": "en" }, "textRegion": { "title": "Text area", "enum": [ "full", "bottom", "top", "custom" ], "type": "string", "description": "Where to look for text. `bottom` = lower 45 % of the frame (subtitles, captions, lower-thirds) and skips signs and logos elsewhere; `top` = upper 45 % (titles, news tickers); `custom` uses \"Custom text area\". A smaller area is also faster.", "default": "full" }, "cropBox": { "title": "Custom text area", "type": "object", "description": "Used when \"Text area\" is `custom`. In percent of the frame: {\"x\": 0, \"y\": 70, \"width\": 100, \"height\": 30} reads only the bottom 30 %." }, "minConfidence": { "title": "Minimum confidence", "minimum": 0.5, "maximum": 0.99, "type": "number", "description": "Text lines read with a lower OCR confidence (0.5-0.99) are dropped. Lower it (0.6) for small or stylised text, raise it (0.85) to drop noise from busy backgrounds.", "default": 0.7 }, "minTextLength": { "title": "Minimum text length (characters)", "minimum": 1, "maximum": 50, "type": "integer", "description": "Ignore text blocks shorter than this (letters and digits only), e.g. stray single letters on a T-shirt.", "default": 2 }, "datasetId": { "title": "Video Frame Extractor dataset (optional)", "type": "string", "description": "Chain from Kanto Labs Video Frame Extractor (or any dataset with image links in `frames[].url`, `url` or `imageUrl`): pick the dataset of a finished run and the text of those frames is read and merged, keeping the original timestamps." }, "frameUrls": { "title": "Frame image URLs (optional)", "type": "array", "description": "Image links (JPG, PNG, WEBP) to read instead of, or as well as, videos - for example the frame links of a Video Frame Extractor run. Their timestamps are taken from Video Frame Extractor file names; other images are read in the given order.", "items": { "type": "string" } }, "maxFramesPerVideo": { "title": "Max frames per video", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper limit of frames read per video. When a video would need more (long video, short interval), frames are spread evenly over the whole video instead. Caps the cost per video at this many frames x the frame price.", "default": 600 }, "maxVideoMinutes": { "title": "Max video length (minutes)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer videos are refused (free).", "default": 120 }, "maxVideoSizeMb": { "title": "Max video size (MB)", "minimum": 1, "maximum": 4000, "type": "integer", "description": "Larger files are refused (free).", "default": 2000 }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 3600, "type": "integer", "description": "Give up on a video that does not download within this time (free).", "default": 600 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }