{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Subtitles, SRT/VTT & RAG Chunks", "description": "Scrape YouTube transcripts and subtitles from any video, playlist or channel. Export text, SRT, VTT or timestamped chunks for RAG and LLM datasets.", "version": "1.0", "x-build-id": "067f9YJUiWdUjDauZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spool~youtube-transcript-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spool-youtube-transcript-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/spool~youtube-transcript-api/runs": { "post": { "operationId": "runs-sync-spool-youtube-transcript-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/spool~youtube-transcript-api/run-sync": { "post": { "operationId": "run-sync-spool-youtube-transcript-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "YouTube videos, channels or playlists", "minItems": 1, "type": "array", "description": "Paste any mix of: video URLs or IDs, playlist URLs, channel URLs (`/@handle`, `/channel/UC...`, `/c/name`). Channels and playlists are expanded automatically into their videos. Accepts watch links, youtu.be, Shorts, embed and live URLs. Duplicates are removed.", "default": [ "https://www.youtube.com/watch?v=aircAruvnKk" ], "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in priority order, e.g. `en`, `es`, `fr`. The first available match wins; a manually written track is always preferred over an auto-generated one in the same language.", "default": [ "en" ], "items": { "type": "string" } }, "includeAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Use YouTube's automatic speech recognition when no human-written captions exist. Turn this off if you only want human-verified text.", "default": true }, "removeCaptionCredits": { "title": "Remove caption credits", "type": "boolean", "description": "Strip translator and reviewer credits from the start and end of the transcript (e.g. \"Translator: … Reviewer: …\", \"Subtitles by the Amara.org community\"). These are not spoken content and pollute the first RAG chunk. Only the first and last few cues are checked.", "default": true }, "translateTo": { "title": "Translate captions to", "type": "string", "description": "Language code to translate captions into, e.g. `fr`, `ar`, `es`, `de`. Uses YouTube's own caption translation, so timestamps are preserved exactly. Leave empty for the original language. Ignored for tracks YouTube marks as untranslatable.", "default": "" }, "maxVideosPerSource": { "title": "Max videos per channel/playlist", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Caps how many videos are taken from EACH channel or playlist. Protects you from accidentally billing a 5,000-video channel. Individual video URLs are never capped.", "default": 50 }, "chunkTranscript": { "title": "Split into RAG chunks", "type": "boolean", "description": "Produce overlapping chunks sized for embedding models. Each chunk keeps its start and end timestamp so retrieved passages stay citable back to the exact moment in the video.", "default": true }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 100, "maximum": 10000, "type": "integer", "description": "Target characters per chunk. Roughly 1000 characters is about 250 tokens, which suits most embedding models.", "default": 1000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Characters repeated between consecutive chunks so a sentence split across a boundary is not lost. Typically 10-20% of chunk size.", "default": 150 }, "outputFormat": { "title": "Output format", "enum": [ "both", "text", "chunks" ], "type": "string", "description": "What text to include in each result.", "default": "both" }, "includeSegments": { "title": "Include raw timed segments", "type": "boolean", "description": "Add the caption cue list with per-line start times and durations. Useful for building subtitle files or precise seeking; makes the dataset considerably larger.", "default": false }, "subtitleFormat": { "title": "Subtitle files", "enum": [ "none", "srt", "vtt", "both" ], "type": "string", "description": "Also produce ready-to-use subtitle files. SRT suits most video editors and players; VTT is the web standard for HTML5 video.", "default": "none" }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to fetch in parallel. Higher values are faster but more likely to hit YouTube rate limits. 3 is a safe default; raise it if your runs stay clean.", "default": 3 }, "maxRetries": { "title": "Max retries per video", "minimum": 1, "maximum": 8, "type": "integer", "description": "Retry attempts for transient failures such as rate limiting or IP blocks. Blocked retries automatically switch to residential proxy. Permanent conditions (no captions, private video) are never retried.", "default": 4 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "YouTube blocks plain datacenter IPs, so Apify Proxy is enabled by default. Residential proxy improves reliability on large runs.", "default": { "useApifyProxy": true } } } }, "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 } } }, "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 } } } } } } } } } }