{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Bulk Scraper - Channel and Playlist", "description": "Get YouTube transcripts in bulk from video links, a whole channel or a playlist. Each row has the full text, timed cues, language and an auto-generated flag, plus title, channel, duration and views. You pay for transcripts, not for the videos it lists. $0.40 per 1,000 transcripts.", "version": "0.1", "x-build-id": "aNF7CAzEK9ggbFj3N" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dami_studio~youtube-transcript-bulk-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dami_studio-youtube-transcript-bulk-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/dami_studio~youtube-transcript-bulk-scraper/runs": { "post": { "operationId": "runs-sync-dami_studio-youtube-transcript-bulk-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/dami_studio~youtube-transcript-bulk-scraper/run-sync": { "post": { "operationId": "run-sync-dami_studio-youtube-transcript-bulk-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", "properties": { "videoUrls": { "title": "Videos, channels or playlists", "minItems": 0, "maxItems": 500, "type": "array", "description": "Mix and match: watch / Shorts / youtu.be / embed links, bare 11-character video IDs, a channel URL or @handle, a bare channel ID (UC...), a playlist link or a bare playlist ID (PL...). Channels and playlists are expanded into their videos for you, and that expansion is never charged.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum transcripts", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard ceiling on how many transcripts this run returns in total, across everything you pasted. This is what you pay for, so keep it low while testing." }, "maxVideosPerSource": { "title": "Videos per channel or playlist", "minimum": 1, "maximum": 2000, "type": "integer", "description": "How deep to go into each channel or playlist before moving to the next one. Channels are read newest first. Ignored for links that already point at a single video." }, "languages": { "title": "Preferred languages", "minItems": 0, "maxItems": 20, "type": "array", "description": "Language codes in priority order, for example en, es, pt-BR. The first one the video actually has is used; pt matches pt-BR. Leave empty to take whatever caption track the video ships with.", "items": { "type": "string" } }, "preferAutoGenerated": { "title": "Prefer auto-generated captions", "type": "boolean", "description": "Off by default, so a human-written caption track wins whenever the video has one - it has punctuation and speaker turns, which auto captions do not. Turn this on if you specifically want the machine transcript.", "default": false }, "captionType": { "title": "Caption type", "enum": [ "any", "human", "auto" ], "type": "string", "description": "Any takes the best track the video has, as before. Human-written only skips a video that has nothing but auto captions; auto-generated only does the reverse. A skipped video gets a free row saying why and is not charged.", "default": "any" }, "publishedAfter": { "title": "Published on or after", "pattern": "^(\\d{4}-\\d{2}-\\d{2}|\\d{1,4} ?days?)$", "type": "string", "description": "Only videos that went up on or after this day: a date like 2026-09-01 (UTC), or a number of days back like 30 days. A channel is read newest first, so the run stops at its first older video. Videos outside the window are skipped before their captions are read and are not charged. A channel or playlist stops after 200 videos outside the window, and its free row says so. Setting a date also adds the upload date to each row." }, "publishedBefore": { "title": "Published before", "pattern": "^(\\d{4}-\\d{2}-\\d{2}|\\d{1,4} ?days?)$", "type": "string", "description": "Only videos that went up before this day, in the same formats. Skipped videos are not charged, and a channel or playlist stops after 200 videos outside the window, with a free row saying so." }, "includeSegments": { "title": "Include timed segments", "type": "boolean", "description": "Keep the per-cue array of start / duration / end / text on each row. Turn it off if you only want the plain transcript text and smaller rows.", "default": true }, "subtitleFormat": { "title": "Subtitle files", "enum": [ "none", "srt", "vtt", "both" ], "type": "string", "description": "Adds the transcript to each row as a ready subtitle file: srt, vtt or both, as text you can save straight to a .srt or .vtt file. Same price per transcript.", "default": "none" }, "includePublishDate": { "title": "Include upload date", "type": "boolean", "description": "Adds publishedAt (when the video went up) and category to each row. It takes one more lookup per video, so the run is a little slower; the price is the same.", "default": false }, "concurrency": { "title": "Videos in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many videos are fetched at the same time. Higher is faster and cheaper per row; lower is gentler if you are pulling several thousand transcripts in one run." }, "proxyUrls": { "title": "Your own proxy servers (optional)", "minItems": 0, "maxItems": 50, "type": "array", "description": "Leave this empty for a normal run. Fill it in only if you want the traffic to leave through proxy servers you already pay for, one URL per line, in the form http://user:pass@host:port.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }