{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript API — Captions to Text, SRT & VTT", "description": "Get the transcript of any YouTube video as timed segments, plain text, SRT or VTT. Picks your preferred language, falls back to auto-generated captions and can machine-translate. Returns title, channel, duration and every available language. Residential proxy included, no API key, no login.", "version": "0.1", "x-build-id": "2dPTM9qnmgfdalTJt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/insight.solutions~youtube-transcript-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-insight.solutions-youtube-transcript-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/insight.solutions~youtube-transcript-api/runs": { "post": { "operationId": "runs-sync-insight.solutions-youtube-transcript-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/insight.solutions~youtube-transcript-api/run-sync": { "post": { "operationId": "run-sync-insight.solutions-youtube-transcript-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "videoUrls" ], "properties": { "videoUrls": { "title": "YouTube videos", "type": "array", "description": "One entry per video. Any YouTube link works — a watch URL, a youtu.be share link, a Shorts, embed or live URL, with or without a playlist or timestamp glued on — and so does a bare 11-character video ID. Channel and playlist URLs are rejected, because they are not one video. Duplicates are fetched, and billed, once.", "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in order of preference, most wanted first, e.g. [\"en\"] or [\"de\",\"en\"]. A human-written track in one of these languages wins; failing that an auto-generated one; failing that a machine translation into one of them, when YouTube offers it. If none of that is possible you still get a transcript — whatever language the video actually has — and the row says which. Every language the video offers is listed in `availableLanguages`, so a fallback is never a mystery.", "default": [ "en" ], "items": { "type": "string" } }, "format": { "title": "Transcript format", "enum": [ "segments", "text", "srt", "vtt" ], "type": "string", "description": "How the transcript is delivered. segments = a `segments` array of {start, duration, text} plus the joined `text`. text = the joined text only, for feeding a model or a search index. srt = a SubRip subtitle file in an `srt` field. vtt = a WebVTT file in a `vtt` field. srt and vtt also carry `text`, and are only added to the row when you pick them — a long talk renders to about 100 KB in each.", "default": "segments" }, "includeTimestamps": { "title": "Include the timed segments", "type": "boolean", "description": "Keep the `segments` array of {start, duration, text}. Turn it off to get only the joined `text` and a much smaller row. It has no effect on the SRT and VTT formats, which carry their timings by definition, and none on the `text` format, which has no segments to begin with.", "default": true }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Fill in `title`, `channelName`, `channelId`, `durationSec` and `publishedAt` from the same response the captions come from. It costs no extra request, so leave it on unless you want the narrowest possible rows.", "default": true }, "maxConcurrency": { "title": "Videos in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many videos are fetched at once. Each parallel worker keeps its own residential proxy session, so a video that gets blocked burns only its own exit IP. Raising this makes a long list finish sooner and makes a block more likely; four is the balance that holds up in practice.", "default": 4 }, "videoTimeoutSecs": { "title": "Per-video timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "The whole budget for one video, spent across every attempt it needs: up to four client contexts, a watch-page fallback, a proxy-session rotation and the caption download. When it runs out the video gets a free `timeout` diagnostic row and the run moves on. Any single request is additionally capped at 15 seconds, so one wedged connection cannot spend the lot.", "default": 30 }, "maxRunSecs": { "title": "Maximum run time (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Wall-clock budget for the whole run. When it is reached the Actor stops fetching, keeps every transcript it already wrote, and writes a free diagnostic row for each video it never reached. Rows already written are still charged; nothing is charged for work that did not happen.", "default": 240 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "YouTube blocks datacenter IP ranges wholesale, which is why this Actor is built around Apify's residential proxy and why the proxy cost is already inside the per-transcript price. Leave this on the default. Sessions rotate automatically when an exit IP is refused. Clearing it sends requests from the run's own datacenter address, which YouTube will almost certainly block.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }