{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - bulk videos, channels, search", "description": "Download YouTube transcripts in bulk for videos, Shorts, channels, playlists or search results. Keyless, with timestamped output and optional AI transcription fallback for videos without captions.", "version": "0.1", "x-build-id": "olWJtmwPj2nhrTjyE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vhsgreed~youtube-transcript-fresh/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vhsgreed-youtube-transcript-fresh", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vhsgreed~youtube-transcript-fresh/runs": { "post": { "operationId": "runs-sync-vhsgreed-youtube-transcript-fresh", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vhsgreed~youtube-transcript-fresh/run-sync": { "post": { "operationId": "run-sync-vhsgreed-youtube-transcript-fresh", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sources": { "title": "Sources (video URLs/IDs, Shorts, playlist URLs, channel URLs/@handles)", "type": "array", "description": "Mix any of: watch?v=..., youtu.be/..., youtube.com/shorts/..., bare 11-char video IDs, youtube.com/playlist?list=..., /channel/UC..., /@handle.", "items": { "type": "string" } }, "searchQueries": { "title": "Search keywords", "type": "array", "description": "YouTube search terms; transcripts for the top results are fetched. Combine with maxVideosPerSource.", "items": { "type": "string" } }, "maxVideosPerSource": { "title": "Max videos per source", "maximum": 2000, "type": "integer", "description": "Applies to each channel, playlist and search query (default 20, max 2000).", "default": 20 }, "proxy": { "title": "Proxy", "enum": [ "apify-residential", "apify-datacenter", "none" ], "type": "string", "description": "YouTube bot-gates datacenter IPs after a few lookups; residential keeps success rates high. Proxy cost is paid by the run owner as platform usage.", "default": "apify-residential" }, "languages": { "title": "Caption languages (fallback order)", "type": "array", "description": "ISO 639-1 codes, tried in order. Empty = original language of the video.", "items": { "type": "string" } }, "captionSource": { "title": "Caption source", "enum": [ "any", "manual", "auto" ], "type": "string", "description": "any = manual preferred; manual = manual captions only; auto = auto-generated only.", "default": "any" }, "translateTo": { "title": "Translate transcript to (ISO 639-1, optional)", "type": "string", "description": "Uses YouTube built-in translation (tlang). Empty = no translation." }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Any of: json (timestamped segments, default), text, srt, vtt, llm (LLM-ready ~1000-char chunks).", "items": { "type": "string" } }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "title, channel, channelId, uploadDate, durationSec, viewCount, likeCount, keywords, thumbnails, description, isLive.", "default": true }, "wordTimestamps": { "title": "Include word-level timestamps when available", "type": "boolean", "description": "Auto-generated (ASR) tracks carry per-word timing; included in each segment as 'words'.", "default": false }, "maxRetries": { "title": "Retries per request", "maximum": 6, "type": "integer", "description": "Retries per YouTube request with exponential backoff (default 3, max 6).", "default": 3 }, "maxVideosForAi": { "title": "Max videos for AI fallback per run", "maximum": 100, "type": "integer", "description": "Cap on caption-less videos sent to Whisper per run (default 5, max 100).", "default": 5 }, "aiEnabled": { "title": "Enable AI transcription fallback (Whisper, for videos without captions)", "type": "boolean", "description": "Off by default. Uses YOUR OpenAI key (aiApiKey or OPENAI_API_KEY env var). Charges ai_transcription_minute per started minute.", "default": false }, "aiApiKey": { "title": "OpenAI API key for AI fallback (BYOK)", "type": "string", "description": "OpenAI key for AI fallback (sk-...). Leave empty to use the OPENAI_API_KEY environment variable." }, "aiMaxMinutes": { "title": "Max AI minutes per run", "maximum": 600, "type": "integer", "description": "Hard cap on Whisper minutes per run (default 30, max 600).", "default": 30 }, "aiMaxVideos": { "title": "Max videos for AI fallback per run", "maximum": 100, "type": "integer", "description": "Cap on caption-less videos sent to Whisper per run (default 5, max 100).", "default": 5 }, "aiDryRun": { "title": "AI dry run (estimate cost only)", "type": "boolean", "description": "When true, reports estimated AI minutes and cost without transcribing or charging.", "default": false } } }, "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 } } } } } } } } } }