{ "openapi": "3.0.1", "info": { "title": "YouTube Video Details Scraper With Subtitles & Translations", "description": "YouTube Video Details Scraper With Subtitles & Translations extracts video details, subtitles, transcripts, translations, titles, descriptions, channels, views, likes, comments, timestamps, and metadata. Ideal for content research, SEO, competitor analysis, and multilingual insights.", "version": "0.1", "x-build-id": "kpqOIZQzxAPIH8NOS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapio~youtube-video-details-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapio-youtube-video-details-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapio~youtube-video-details-scraper/runs": { "post": { "operationId": "runs-sync-scrapio-youtube-video-details-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapio~youtube-video-details-scraper/run-sync": { "post": { "operationId": "run-sync-scrapio-youtube-video-details-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "đŸŽŦ YouTube Video URLs or IDs", "type": "array", "description": "One entry per video. Accepts `https://www.youtube.com/watch?v=ID`, `https://youtu.be/ID`, `/shorts/ID`, `/live/ID`, `/embed/ID` and bare 11-character video IDs.\n\nPlaylist and channel URLs are **rejected with a reason** instead of silently producing a malformed row.\n\nExample: `dQw4w9WgXcQ` and `https://youtu.be/jNQXAC9IVRw`.", "items": { "type": "string" } }, "subtitlesLanguage": { "title": "🌐 Subtitle Language", "type": "string", "description": "ISO code of the caption track you want, e.g. `en`, `en-US`, `es`, `de`, `pt-BR`, `hi`, `ja`. Matching is exact first, then case-insensitive, then base-language (`en` also matches `en-US`).\n\nLeave empty to use the video's own language, then English, then the first track available.\n\nExample: `es` → the Spanish track when the video has one.", "default": "" }, "captionSource": { "title": "🎙ī¸ Human vs Auto-Generated Captions", "enum": [ "human_first", "auto_first", "human_only", "auto_only" ], "type": "string", "description": "Which caption pool to read from. `human_first` (default) prefers creator-uploaded subtitles and falls back to YouTube's speech recognition. `auto_first` inverts that. The `_only` options never fall back and instead return a reason.\n\nExample: `auto_only` on a video whose only track is a creator upload → `transcript: null`, `noTranscriptReason: no_auto_captions_available`.", "default": "human_first" }, "subtitlesFormat": { "title": "đŸ“Ļ Subtitle Output Format", "enum": [ "timestamped", "plaintext", "srt", "vtt" ], "type": "string", "description": "`timestamped` and `plaintext` are always produced (`transcript` and `transcriptText`). Choosing `srt` or `vtt` additionally downloads that exact format **natively from YouTube** into `transcriptSrt` / `transcriptVtt` — nothing is transcoded here.\n\nExample: `srt` → a ready-to-use `.srt` body you can save straight to disk.", "default": "timestamped" }, "translateTranscriptTo": { "title": "🌍 Auto-Translate Transcript To", "type": "string", "description": "ISO code for a **second** transcript translated by YouTube's own `tlang` parameter — no third-party translation service and no API key. The original-language transcript is still returned alongside it.\n\nExample: `es` → `translatedTranscript` and `translatedTranscriptText` in Spanish, with `translatedToLanguage: \"es\"`.\n\nLeave empty to skip translation. If translation is impossible you get `noTranslationReason` instead of a silent blank.", "default": "" }, "allowLanguageFallback": { "title": "↩ī¸ Fall Back To Another Language", "type": "boolean", "description": "When the requested **Subtitle Language** does not exist on a video: `true` (default) picks the best available track instead; `false` returns `transcript: null` with `noTranscriptReason: language_not_available`.\n\nSet this to `false` when you only want rows in one specific language.", "default": true }, "skipVideosWithoutTranscript": { "title": "đŸšĢ Skip Videos With No Captions", "type": "boolean", "description": "`true` drops videos that have no usable caption track entirely — no dataset row, no charge. `false` (default) still returns the full metadata row with `hasTranscript: false` and a `noTranscriptReason`.", "default": false }, "includeChannelLogo": { "title": "đŸ–ŧī¸ Fetch Channel Avatar", "type": "boolean", "description": "Fills `channel.logo` by loading the channel's About page (~1.9 MB). Results are cached per channel within a run, so ten videos from one channel cost one request, not ten. Turn this off for the fastest possible runs.", "default": true }, "proxyConfiguration": { "title": "🔗 Proxy", "type": "object", "description": "YouTube bot-walls datacenter and container-native IPs hard on repeated video extractions — measured 1 of 8 videos on datacenter versus 7 of 8 on residential. The default below is therefore **Apify RESIDENTIAL**, which costs more per GB but is the only route with a workable success rate.\n\nIf a request is bot-walled the Actor escalates the route (direct → datacenter → residential) and rotates the session rather than just sleeping.", "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 } } } } } } } } } }