{ "openapi": "3.0.1", "info": { "title": "Video to LLM Context - Keyframes, Transcript & Scenes for AI", "description": "Turn any video file into context an AI agent can read: scene list, one keyframe image per scene, Whisper transcript aligned to each scene, a keyframe grid and a ready-to-paste text block. No LLM inside. $0.002 per keyframe + $0.008 per audio minute.", "version": "1.0", "x-build-id": "nNXnvtkuch2gaRODR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kantolabs~video-to-llm-context/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kantolabs-video-to-llm-context", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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-to-llm-context/runs": { "post": { "operationId": "runs-sync-kantolabs-video-to-llm-context", "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-to-llm-context/run-sync": { "post": { "operationId": "run-sync-kantolabs-video-to-llm-context", "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", "required": [ "videoUrls" ], "properties": { "videoUrls": { "title": "Video file 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 (public or pre-signed URLs), CDNs, an Apify key-value store, Dropbox and Google Drive share links (shared as 'anyone with the link') all work. Pages of platforms such as YouTube, TikTok or Instagram are refused.", "default": [ "https://api.apify.com/v2/key-value-stores/aXcXwfChlioPWAUJv/records/sample-vertical-talk.mp4?signature=105QVevs72w3z5gMQzgIJ" ], "items": { "type": "string" } }, "maxKeyframes": { "title": "Max scenes / keyframes per video", "minimum": 1, "maximum": 100, "type": "integer", "description": "Upper limit of scenes per video; each scene gets one keyframe image ($0.002 each). The strongest cuts are kept first. 8-16 suits most AI prompts; long videos without cuts are split into parts of at most 'Max scene length'.", "default": 12 }, "transcribe": { "title": "Transcribe speech", "type": "boolean", "description": "Transcribe the audio track with Whisper and align the words to each scene ($0.008 per started audio minute). Videos without speech or audio are not charged for audio. Turn off for keyframes only.", "default": true }, "language": { "title": "Spoken language", "pattern": "^(auto|[a-zA-Z]{2,3})$", "type": "string", "description": "'auto' detects the language. Or a 2-letter ISO 639-1 code (en, es, de, fr, pt, ja, zh...) to skip detection - recommended for short clips.", "default": "auto" }, "sceneThreshold": { "title": "Scene cut sensitivity", "enum": [ "0.15", "0.2", "0.3", "0.4", "0.5" ], "type": "string", "description": "Minimum ffmpeg scene score (0-1) that counts as a cut. Lower finds subtler changes.", "default": "0.3" }, "minSceneSeconds": { "title": "Min scene length (seconds)", "minimum": 1, "maximum": 60, "type": "integer", "description": "Cuts closer together than this are merged, so fast montages do not produce a flood of tiny scenes.", "default": 2 }, "maxSceneSeconds": { "title": "Max scene length (seconds)", "minimum": 5, "maximum": 3600, "type": "integer", "description": "Shots longer than this (talking heads, screen recordings) are split into equal parts at pauses in the speech, while the scene limit allows. Real cuts are never moved.", "default": 60 }, "gridImage": { "title": "Keyframe grid image (free)", "type": "boolean", "description": "Also save ONE image with every keyframe tiled and labelled (scene number + time) - send a single image to a vision model instead of many. Not charged.", "default": true }, "includeImageUrlsInContext": { "title": "Image links in llmContext", "type": "boolean", "description": "Put the keyframe and grid image links into the plain-text llmContext field. Turn off for a shorter text block (links stay in the scenes list).", "default": true }, "keyframeMaxWidth": { "title": "Max keyframe width (px)", "minimum": 0, "maximum": 4096, "type": "integer", "description": "Keyframes wider than this are scaled down (aspect kept). 1024 is a good size for vision models. 0 = original size.", "default": 1024 }, "imageFormat": { "title": "Image format", "enum": [ "jpg", "png", "webp" ], "type": "string", "description": "Format of the keyframe images.", "default": "jpg" }, "imageQuality": { "title": "JPEG / WEBP quality", "minimum": 30, "maximum": 100, "type": "integer", "description": "30-100.", "default": 85 }, "skipBlankFrames": { "title": "Skip black / blank keyframes", "type": "boolean", "description": "When a keyframe is black or one flat colour, step forward up to 2 seconds inside the scene to a frame with content; if none, that scene has no image and it is not charged.", "default": true }, "maxDurationMinutes": { "title": "Max video duration (minutes)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Longer videos are skipped (free). Up to 300.", "default": 120 }, "maxVideoSizeMb": { "title": "Max video size (MB)", "minimum": 1, "maximum": 4000, "type": "integer", "description": "Larger files are skipped (free).", "default": 1000 }, "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 } } } } } } } } } }