{ "openapi": "3.0.1", "info": { "title": "YouTube Transcripts Scraper: Text, Timed Segments, SRT", "description": "YouTube transcripts (full text, timed segments, language, auto-generated flag) for videos, Shorts, channels or playlists; from $2.48 per 1,000 transcripts. Caption languages, title, channel, date, views, srt/vtt. Videos without captions are free error rows.", "version": "0.1", "x-build-id": "XSVFr9qaTphP5nwEV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/arcadium~youtube-transcripts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-arcadium-youtube-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/arcadium~youtube-transcripts/runs": { "post": { "operationId": "runs-sync-arcadium-youtube-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/arcadium~youtube-transcripts/run-sync": { "post": { "operationId": "run-sync-arcadium-youtube-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": { "urls": { "title": "YouTube URLs or video IDs", "type": "array", "description": "Example: https://www.youtube.com/watch?v=dQw4w9WgXcQ, https://youtu.be/dQw4w9WgXcQ, a Shorts URL, a bare video ID (dQw4w9WgXcQ), a channel (https://www.youtube.com/@kurzgesagt, add /shorts or /streams for those tabs) or a playlist URL. Channels and playlists give up to maxVideosPerSource videos each, channels newest first.", "items": { "type": "string" } }, "languages": { "title": "Preferred caption languages", "type": "array", "description": "ISO language codes in order of preference, e.g. [\"en\", \"de\"]; en also matches en-US and en-GB. The first one the video has is used. Empty or none available: the original spoken language (languageMatched is false when none matched).", "items": { "type": "string" } }, "captionType": { "title": "Caption type", "enum": [ "any", "manual", "auto" ], "type": "string", "description": "Values: any (uploaded captions first, else auto-generated), manual (uploaded by the creator only), auto (YouTube speech recognition only). Videos without that type give a free error row. Default: any." }, "translateTo": { "title": "Translate to", "type": "string", "description": "ISO language code, e.g. es. A native track in that language is used when the video has one (translationStatus original). Otherwise YouTube's own machine translation is asked for; YouTube currently refuses it for anonymous clients, so you get the original with translationStatus unavailable." }, "maxVideosPerSource": { "title": "Max videos per channel or playlist", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Transcripts per channel or playlist URL, 1 to 5,000 (default 50). Videos without captions or outside the date range do not count. Direct video URLs are not limited by this." }, "publishedAfter": { "title": "Published on or after", "type": "string", "description": "Date as YYYY-MM-DD, e.g. 2026-01-01. Videos published earlier are skipped for free; on a channel the listing stops at the first older videos." }, "publishedBefore": { "title": "Published on or before", "type": "string", "description": "Date as YYYY-MM-DD, e.g. 2026-06-30. Videos published later are skipped for free." }, "includeSegments": { "title": "Include timed segments", "type": "boolean", "description": "Adds segments: one entry per caption line with start and duration in seconds and its text. The joined transcript text is always included.", "default": true }, "subtitleFormat": { "title": "Subtitle file text", "enum": [ "none", "srt", "vtt" ], "type": "string", "description": "Values: none, srt, vtt. srt or vtt adds the captions as a ready subtitle file in the srt or vtt field. Default: none." }, "description": { "title": "Video description", "enum": [ "short", "full", "none" ], "type": "string", "description": "Values: short (about 300 characters, default), full, none. Emails and phone numbers are removed.", "default": "short" }, "maxResults": { "title": "Max transcripts in total", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stops the run after this many transcripts across all URLs, 1 to 1,000,000. A cost cap; leave empty for no limit." }, "includeErrorRows": { "title": "Add a row for videos without a transcript", "type": "boolean", "description": "Adds a free row (rowType error, with a code and message) for every video or URL that gave no transcript: no captions, private, age-restricted, not found. On by default.", "default": true }, "maxRetries": { "title": "Retries per request", "minimum": 0, "maximum": 10, "type": "integer", "description": "Advanced. How often a request is retried after a temporary error, 0 to 10.", "default": 5 }, "proxyConfiguration": { "title": "Proxy (advanced)", "type": "object", "description": "Advanced. Leave empty: the actor starts on datacenter proxies and moves to residential when YouTube asks to confirm you are not a bot." } } }, "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 } } } } } } } } } }