{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript & RAG Chunker", "description": "Get the full transcript of any YouTube video, playlist, channel or search - as plain text, SRT/VTT, or RAG-ready token-window chunks (overlap, dedup, token counts, deep links). Transcript-only or transcript + chunks, your choice. Multi-language + translation. Per-video pricing.", "version": "0.2", "x-build-id": "ZL8qN6aVqFhPxwK2g" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leaderly_jackpine~youtube-rag-transcripts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leaderly_jackpine-youtube-rag-transcripts", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leaderly_jackpine~youtube-rag-transcripts/runs": { "post": { "operationId": "runs-sync-leaderly_jackpine-youtube-rag-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leaderly_jackpine~youtube-rag-transcripts/run-sync": { "post": { "operationId": "run-sync-leaderly_jackpine-youtube-rag-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "minItems": 1, "maxItems": 1000, "type": "array", "description": "YouTube video (youtube.com/watch?v=... or youtu.be/...), playlist (youtube.com/playlist?list=...), channel (youtube.com/@handle, /channel/UC..., /c/Name or /user/Name, with or without /videos) or search (youtube.com/results?search_query=) URLs.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries (optional)", "maxItems": 100, "type": "array", "description": "Free-text search queries; each is run on YouTube and its result videos are enqueued (capped by maxVideos).", "items": { "type": "string" } }, "languages": { "title": "Preferred caption languages", "type": "array", "description": "Preferred caption languageCodes in priority order (e.g. ['en','en-US']). The first match present on the video wins.", "items": { "type": "string" } }, "captionPreference": { "title": "Caption preference", "enum": [ "manual", "auto" ], "type": "string", "description": "manual = prefer human captions, fall back to auto-generated (ASR); auto = prefer ASR.", "default": "manual" }, "translateTo": { "title": "Translate to (optional)", "type": "string", "description": "Optional translation languageCode appended as &tlang to the caption baseUrl (e.g. 'es'). When set, the chosen track is translated into this language." }, "chunkSizeTokens": { "title": "Chunk size (tokens)", "minimum": 128, "maximum": 8192, "type": "integer", "description": "Target maximum tokens per chunk in tokenWindow mode (128-8192). Chunks are segment-aligned so a chunk may slightly exceed this when a single caption segment is larger.", "default": 512 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 512, "type": "integer", "description": "Overlap tokens carried into the next chunk in tokenWindow mode (0-512). Must be smaller than chunk size.", "default": 64 }, "chunkingMode": { "title": "Chunking mode", "enum": [ "tokenWindow", "timestampWindow" ], "type": "string", "description": "tokenWindow = greedily pack segments up to chunk size with overlap; timestampWindow = one chunk per fixed-length time window.", "default": "tokenWindow" }, "timestampWindowSeconds": { "title": "Timestamp window (seconds)", "minimum": 10, "maximum": 600, "type": "integer", "description": "Length of each time window in timestampWindow mode (10-600).", "default": 60 }, "tokenizerModel": { "title": "Tokenizer", "enum": [ "o200k_base", "cl100k_base" ], "type": "string", "description": "Tokenizer used for token counts. o200k_base matches GPT-4o/4.1/o-series; cl100k_base matches GPT-4/3.5. Note: counts are estimates for non-OpenAI models (Claude/embeddings may differ 5-15%).", "default": "o200k_base" }, "outputFormats": { "title": "Output formats", "uniqueItems": true, "type": "array", "description": "What to emit per video. chunkRows = flat chunk rows (one per line, free, ideal for JSONL/RAG ingestion); json = per-video summary row with nested chunks (charged); srt/vtt/txt = subtitle/plain-text transcript attached to the summary row; markdown = transcript with timestamp headings + deep links.", "items": { "type": "string" }, "default": [ "chunkRows", "json" ] }, "includeRagChunks": { "title": "Include RAG chunks", "type": "boolean", "description": "ON (default) = transcript + RAG-ready token-window chunks (flat chunk rows per video). OFF = transcript-only mode: one clean row per video with the full transcript (no chunk rows, no chunking). Use OFF when you just want the transcript text of each video.", "default": true }, "maxVideos": { "title": "Max videos", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard cap on the number of videos processed across all sources (1-1000). Listing videos beyond this are skipped.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy. Residential with US country pin is the default: datacenter egress can be bot-flagged and silently return no captionTracks.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }