{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper · Chinese-first, AI fallback", "description": "Get transcripts from YouTube videos - Chinese first. Only ~25-37% of Chinese videos have captions; this Actor transcribes the rest with AI.", "version": "0.1", "x-build-id": "NpwgfeRmNGbCKC8zx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blue59~youtube-chinese-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blue59-youtube-chinese-transcript", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blue59~youtube-chinese-transcript/runs": { "post": { "operationId": "runs-sync-blue59-youtube-chinese-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blue59~youtube-chinese-transcript/run-sync": { "post": { "operationId": "run-sync-blue59-youtube-chinese-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "影片網址 / Video URLs", "type": "array", "description": "YouTube 影片、頻道或播放清單網址。也接受 11 碼影片 ID。Accepts video, channel, or playlist URLs.", "items": { "type": "string" } }, "maxItems": { "title": "最多處理幾支 / Max videos", "minimum": 1, "maximum": 1000, "type": "integer", "description": "從頻道或播放清單展開時的上限。Cap when expanding a channel or playlist.", "default": 50 }, "preferredLanguages": { "title": "語言優先序 / Language preference", "type": "array", "description": "人工字幕依序尋找，先找到先用，預設繁中優先。只有自動字幕的影片，預設給影片原本講的語言（見下方「自動字幕給原文」選項，關閉後才照此順序挑，可能是 YouTube 機器翻譯軌）。Human-made caption tracks are tried in order (Traditional Chinese first by default). For videos with only auto-captions, the spoken language is returned by default — see the option below.", "default": [ "zh-Hant", "zh-TW", "zh-HK", "zh-Hans", "zh-CN", "zh", "en" ], "items": { "type": "string" } }, "autoCaptionOriginalLanguage": { "title": "自動字幕給原文 / Auto-captions in original language", "type": "boolean", "description": "只影響「只有自動字幕」的影片。開(預設)=給影片原本講的語言(英文影片給英文、日文影片給日文),不給 YouTube 的機器翻譯軌。關=照上方語言優先序挑,英文影片可能拿到 YouTube 機器翻譯的中文。人工字幕不受影響。Only affects videos that have auto-captions only. On (default): return the language actually spoken, skipping YouTube's machine-translated tracks. Off: pick by Language preference, which may return a machine-translated track (e.g. Chinese for an English video). Human-made captions are unaffected.", "default": true }, "subtitleFormats": { "title": "字幕檔輸出 / Subtitle files (SRT / VTT)", "type": "array", "description": "另外產出帶時間軸的字幕檔:可選 SRT、WebVTT。每筆結果會多 `segments`(起訖秒數+文字)與 `srt`/`vtt` 欄位,免費附加不另收費。留空=只要純文字逐字稿。來源沒有時間軸時會附 `subtitleNote` 說明。Free add-on: timestamped subtitle files plus `segments`. Leave empty for plain transcripts only.", "items": { "type": "string", "enum": [ "srt", "vtt" ], "enumTitles": [ "SRT (.srt)", "WebVTT (.vtt)" ] }, "default": [] }, "aiFallback": { "title": "沒字幕時用 AI 轉錄 / AI fallback when no captions", "type": "boolean", "description": "實測:中文影片只有約 25-37% 有字幕。開啟後，沒有字幕的影片會下載音訊並用 Groq Whisper 轉錄。需填下方金鑰。Measured: only ~25-37% of Chinese videos have captions. Requires your Groq key below." }, "groqApiKey": { "title": "Groq API 金鑰 / Groq API key", "type": "string", "description": "只在開啟 AI 補位時需要。免費申請:https://console.groq.com (免費層每日 2,000 次)。你的金鑰不會被儲存。Only needed for AI fallback; free tier available. Never stored." }, "minChars": { "title": "最少字數 / Minimum characters", "minimum": 0, "type": "integer", "description": "低於此字數視為抓取失敗，不列入結果(防止交出垃圾資料)。Results below this are treated as failures.", "default": 30 }, "proxyConfiguration": { "title": "代理設定 / Proxy", "type": "object", "description": "建議開啟。YouTube 會擋機房 IP。Recommended - YouTube blocks datacenter IPs.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }