{ "openapi": "3.0.1", "info": { "title": "CJK-Accurate Audio Transcriber (Whisper) - Traditional Chinese", "description": "Transcribe audio/video URLs with Whisper large-v3-turbo via Groq. Correct Traditional Chinese (Taiwan phrasing) or Simplified output via OpenCC, plus SRT/VTT/segments. Pay per audio minute; bring your own Groq key for a lower rate.", "version": "0.1", "x-build-id": "WRSRDtuY0JcRmUq3a" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/flyingfishclaw~cjk-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-flyingfishclaw-cjk-transcriber", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/flyingfishclaw~cjk-transcriber/runs": { "post": { "operationId": "runs-sync-flyingfishclaw-cjk-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/flyingfishclaw~cjk-transcriber/run-sync": { "post": { "operationId": "run-sync-flyingfishclaw-cjk-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "audioUrls" ], "properties": { "audioUrls": { "title": "Audio / video URLs", "type": "array", "description": "Direct http(s) links to media files (mp3, m4a, wav, ogg, mp4, mkv, podcast enclosures...). One dataset item is produced per URL. The prefilled sample is a 1-minute Mandarin spoken-Wikipedia clip (CC licence) so you can try the Actor immediately.", "default": [ "https://upload.wikimedia.org/wikipedia/commons/d/d0/%E7%B6%AD%E5%9F%BA%E7%99%BE%E7%A7%91-%E4%B8%AD%E8%8F%AF%E6%B0%91%E5%9C%8B.ogg" ], "items": { "type": "string" } }, "language": { "title": "Spoken language", "enum": [ "auto", "zh", "en", "ja", "ko", "yue", "de", "fr", "es", "pt", "it", "ru", "vi", "th", "id", "ms", "ar", "hi" ], "type": "string", "description": "ISO 639-1 code. 'auto' lets Whisper detect it. For Chinese audio set 'zh' - it enables the Traditional-Chinese prompt and gives the best script consistency.", "default": "auto" }, "chineseScript": { "title": "Chinese script", "enum": [ "auto", "traditional", "simplified", "none" ], "type": "string", "description": "Applied only when the detected/selected language is Chinese. 'auto' and 'traditional' convert to Traditional Chinese with Taiwan phrasing (OpenCC s2twp, e.g. 软件→軟體). 'simplified' converts to Simplified. 'none' leaves Whisper output untouched.", "default": "auto" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "text and segments go into the dataset item; srt/vtt files are saved to the key-value store and linked from the item.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timed segments (JSON)", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments", "srt" ] }, "model": { "title": "Whisper model", "enum": [ "whisper-large-v3-turbo", "whisper-large-v3" ], "type": "string", "description": "Groq-hosted Whisper model. large-v3-turbo is faster and cheaper; large-v3 is slightly more accurate on difficult audio.", "default": "whisper-large-v3-turbo" }, "initialPrompt": { "title": "Initial prompt (optional)", "type": "string", "description": "Up to 500 characters of context (names, jargon, preferred spelling). For zh + Traditional a Taiwan-style prompt is used automatically when left empty." }, "filterHallucinations": { "title": "Drop Whisper hallucinations", "type": "boolean", "description": "Removes text Whisper invents over silence or music: known subtitle boilerplate (e.g. 請不吝點贊…明鏡與點點欄目, Amara.org credits), punctuation-only segments, segments that echo the built-in Chinese prompt (your own initialPrompt is never echo-checked), segments of 15 s or more with under 1 letter/character per second (punctuation not counted), and Whisper's own no-speech / repetition-loop signals. The count is reported as droppedSegments (null when this is off); an empty result carries emptyTranscript: true, plus allSegmentsDropped: true when the filter removed everything. Turn off for very sparse speech.", "default": true }, "chunkMinutes": { "title": "Chunk length (minutes)", "minimum": 1, "maximum": 20, "type": "integer", "description": "Long files are split into chunks of this length before transcription (1-20). 10 keeps every chunk under Groq's 25 MB limit.", "default": 10 }, "maxFileSizeMb": { "title": "Max download size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Downloads larger than this are rejected before any transcription cost is incurred.", "default": 500 }, "maxDurationMinutes": { "title": "Max media duration (minutes)", "minimum": 1, "maximum": 1440, "type": "integer", "description": "Files longer than this are rejected (status too_long).", "default": 240 }, "groqApiKey": { "title": "Your Groq API key (optional, cheaper rate)", "type": "string", "description": "Bring your own key to be billed at the lower 'audio-minute-byok' event price. Leave empty to use the hosted key." } } }, "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 } } } } } } } } } }