{ "openapi": "3.0.1", "info": { "title": "Whisper Audio & Podcast Transcriber (SRT, VTT, Translate)", "description": "Transcribe audio/video files or podcast RSS episodes with Whisper running inside the Actor (no third-party API). Text, timestamps, SRT/VTT, language detection, optional English translation. Only transcribe recordings you have rights and consent to.", "version": "0.1", "x-build-id": "bSv1Q6RgXf2MywY9Q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/steady_kahikatea~whisper-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-steady_kahikatea-whisper-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/steady_kahikatea~whisper-transcriber/runs": { "post": { "operationId": "runs-sync-steady_kahikatea-whisper-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/steady_kahikatea~whisper-transcriber/run-sync": { "post": { "operationId": "run-sync-steady_kahikatea-whisper-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "audioUrls": { "title": "Audio/video files (upload or direct URLs)", "type": "array", "description": "Upload recordings or paste direct links to audio/video files you have the right and consent to transcribe. Video/social platform links (YouTube, TikTok, Instagram, Vimeo, X, Facebook…) are rejected. Max 10 files per run, 500 MB and 120 minutes each." }, "rssFeeds": { "title": "Podcast RSS feeds", "type": "array", "description": "Podcast feed URLs. The latest N episodes of each feed are transcribed (counted toward the 10-file limit).", "items": { "type": "string" } }, "latestEpisodes": { "title": "Latest episodes per feed", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many of the newest episodes to transcribe from each feed.", "default": 1 }, "quality": { "title": "Model / quality", "enum": [ "fast", "standard", "accurate" ], "type": "string", "description": "fast = Whisper base (cheapest, good for clear English). standard = Whisper small (better accuracy and languages). accurate = Whisper large-v3-turbo (best accuracy, especially non-English; slowest).", "default": "standard" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "transcribe = text in the spoken language. translate = English translation (uses the fast or standard model).", "default": "transcribe" }, "language": { "title": "Language (optional)", "type": "string", "description": "ISO code such as en, es, de, ja. Leave empty to auto-detect." }, "skipSilence": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Skips non-speech parts; reduces hallucinations on music/silence.", "default": true }, "beamSearch": { "title": "Beam search (slower, slightly more accurate)", "type": "boolean", "description": "Use beam size 5 instead of greedy decoding.", "default": false }, "includeSubtitles": { "title": "Include SRT/VTT in dataset", "type": "boolean", "description": "SRT and VTT are always saved as files; this also embeds them in each dataset row.", "default": 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 } } } } } } } } } }