{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Subtitles & Captions, $0.001/Video", "description": "Extract YouTube transcripts, subtitles, and captions (uploaded or auto-generated) as JSON with per-line timestamps from youtube.com/watch and youtu.be links. $0.001 per transcript. Pick a caption language, run in bulk, reshape output. No API key or login. For AI, RAG, SEO, and research.", "version": "0.0", "x-build-id": "VCjEfvCtQsEBw7amI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/apidojo~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-apidojo-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/apidojo~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-apidojo-youtube-transcript-scraper", "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/apidojo~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-apidojo-youtube-transcript-scraper", "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": [ "startUrls" ], "properties": { "startUrls": { "title": "YouTube video URLs", "type": "array", "description": "One YouTube video link per entry. Supported: youtube.com/watch?v=VIDEO_ID (also m. and music. subdomains) and youtu.be/VIDEO_ID. Not supported: Shorts, live, embed, playlist and channel links. To start from a playlist or channel, get its video links with apidojo/youtube-playlist-scraper or apidojo/youtube-channel-scraper first. Plain URL strings; objects like {\"url\": \"...\"} also work. Duplicate links return duplicate rows.", "items": { "type": "string" } }, "lang": { "title": "Transcript language code", "type": "string", "description": "Optional caption language code, such as en, es, de, tr or pt-BR. Auto-generated captions count: en can return \"English (auto-generated)\". Leave empty to get the video's default caption track. If the video has no track in that language, a different track is returned instead, so check the output's selected.languageCode to see which one you got." }, "maxItems": { "title": "Maximum transcripts to save", "type": "integer", "description": "Optional. The run stops saving once this many rows are in the dataset. Leave empty to process every URL. Runs on the free Apify plan are capped at 10 rows." }, "customMapFunction": { "title": "Custom map function (JavaScript)", "type": "string", "description": "Optional. Leave empty to save the full transcript object. Otherwise, a JavaScript function that receives one transcript object and returns the object to save, e.g. (o) => ({ id: o.id, text: o.transcript.map(l => l.text).join(' ') }). It must return an object and can't drop rows. inputSource is always kept. If the function throws, the unmodified object is saved." }, "outputConnector": { "title": "Send results to Notion, Todoist, … (optional)", "type": "string", "description": "Pick an MCP connector you authorized in Console → Settings → API & Integrations → MCP connectors (e.g. Notion, Todoist — any service whose MCP server offers non-destructive write tools works best-effort). The scraped results are written through your own connector — the Actor never sees your third-party credentials. Only non-destructive write tools are used; it can never delete or overwrite your existing data." }, "deliverTarget": { "title": "Destination target", "type": "string", "description": "Where to write into the connector — paste the URL or ID. Notion example: https://www.notion.so/My-Posts-24f8a1b2c3d44e5f8a9b0c1d2e3f4a5b. Leave empty for services that need no target (e.g. Todoist Inbox, Slack). For Notion, share the page or database with your connector first (Notion's ••• → Connections menu), and point at a PAGE for structured columns (the Actor builds the database for you) — an empty database receives only the title (the rest of each record goes to the row's body)." }, "deliverMode": { "title": "Write mode", "enum": [ "perPost", "summary" ], "type": "string", "description": "perPost writes one record per scraped item; summary writes a single roll-up for the run.", "default": "perPost" }, "deliverMaxItems": { "title": "Max records to deliver — perPost only (optional)", "minimum": 1, "type": "integer", "description": "Cap on how many records perPost mode writes to the connector; ignored in summary mode. Leave empty to deliver everything scraped." } } }, "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 } } } } } } } } } }