{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript & Subtitles Scraper API", "description": "Get YouTube transcripts and captions from videos, playlists and channels as timed segments, plain text, SRT or VTT. Many languages, an auto-generated fallback and video metadata. Each failed video gets a clear error row and the run never hangs. Built for AI and RAG pipelines.", "version": "0.1", "x-build-id": "24H4K4oRLEeiPq3BV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zovo-one~tubetext-youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zovo-one-tubetext-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zovo-one~tubetext-youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-zovo-one-tubetext-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zovo-one~tubetext-youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-zovo-one-tubetext-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "YouTube videos, playlists or channels", "type": "array", "description": "Paste YouTube videos, playlists or channels, one per line, in any mix. Videos: watch URL, youtu.be link, Shorts URL or an 11-character video id (for example jNQXAC9IVRw). Playlists: https://www.youtube.com/playlist?list=PL... or the playlist id. Channels: https://www.youtube.com/@handle, @handle, /channel/UC..., /c/name or a UC... id (the latest uploads are used). A watch URL that also has &list= is read as the single video. YouTube Mix playlists (RD...) are not supported. Duplicates are removed. The prefilled two videos make a quick test run of about $0.005.", "default": [ "https://www.youtube.com/watch?v=jNQXAC9IVRw", "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ], "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in order of preference, for example en, de, es, pt-BR, ja. For each language, a caption track written by a person is used before an auto-generated one. \"en\" also accepts regional tracks such as en-US or en-GB. Up to 10 codes.", "default": [ "en" ], "items": { "type": "string" } }, "allowAutoGenerated": { "title": "Use auto-generated captions", "type": "boolean", "description": "Use YouTube's automatic (speech-recognition) captions when no caption track written by a person exists in your languages. Most videos only have auto-generated captions, so leave this on unless you need human-made captions only.", "default": true }, "fallbackToAnyLanguage": { "title": "Fall back to the video's own language", "type": "boolean", "description": "If none of your preferred languages exists, return the transcript in the video's original language (languageMatched = false on the row). Turn off to get an error row (NO_TRANSCRIPT_IN_LANGUAGE) instead, which is not charged.", "default": true }, "outputFormat": { "title": "Output format", "enum": [ "segments", "text", "srt", "vtt" ], "type": "string", "description": "Every row has the full plain text in \"text\". Choose what else to add: timestamped segments (start and duration in seconds, good for search and citations), an SRT subtitle file or a WebVTT subtitle file. Pick \"Plain text only\" for the smallest rows when you feed transcripts to an LLM.", "default": "segments" }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Adds title, channel name and id, publish date, duration, view count and category to each row. Turn off for slightly faster runs (one request less per video).", "default": true }, "maxVideosPerSource": { "title": "Max videos per playlist or channel", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Playlists: the first N videos in playlist order. Channels: the latest N uploads (Shorts and past live streams count as uploads). Listing is free; each video is charged only if its transcript is saved. Example: 20 videos with captions cost $0.05.", "default": 20 }, "maxTotalVideos": { "title": "Max videos per run", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on the number of videos in one run, across all inputs, after duplicates are removed. Use it as a safety limit for large channels.", "default": 1000 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "YouTube blocks many datacenter IPs, so the residential group is the reliable choice. If a request is blocked, the Actor retries the video through a new proxy session. If the proxy can't be set up, the run continues without one and logs a warning.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many videos are read in parallel (1 to 10). Keep it low (1 to 5) to avoid YouTube rate limits.", "default": 3 }, "maxRetries": { "title": "Retries per video", "minimum": 0, "maximum": 5, "type": "integer", "description": "Extra attempts for a video after a block, rate limit or network error, each through a new proxy session when a proxy is on. Permanent errors such as private or age-restricted videos are not retried.", "default": 2 } } }, "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 } } } } } } } } } }