{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber (Whisper)", "description": "Transcribe audio and video files from direct URLs into text, timestamped segments, SRT or VTT with Whisper. Optional high-precision mode for Portuguese and noisy audio. Pay per minute, no YouTube or social platform downloads.", "version": "0.1", "x-build-id": "DQmcSUFtdFj4p4vd2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plum_spear~aztec-audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plum_spear-aztec-audio-video-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/plum_spear~aztec-audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-plum_spear-aztec-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/plum_spear~aztec-audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-plum_spear-aztec-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mediaUrls" ], "properties": { "mediaUrls": { "title": "Media file URLs", "minItems": 1, "type": "array", "description": "Direct links to audio or video files (mp3, wav, m4a, aac, flac, ogg, opus, mp4, webm, mkv, mov). Each link must return the file itself, not a web page. To transcribe a file you uploaded to an Apify key-value store, use the record's public URL (with its signature). YouTube, Instagram, TikTok and similar platforms are refused.", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "ISO 639-1 code of the spoken language (for example 'en', 'pt', 'es', 'de'). Use 'auto' to detect it from the audio.", "default": "auto" }, "quality": { "title": "Quality", "enum": [ "standard", "high" ], "type": "string", "description": "'standard' runs Whisper base inside this Actor: your audio never leaves the run. 'high' sends the audio to Groq (United States) to be transcribed with whisper-large-v3-turbo, which is clearly more accurate, especially in Portuguese and in noisy audio. With 'high', your audio is processed by a third party; do not use it for confidential material. If Groq is unavailable for a block, that block is transcribed on this Actor's CPU and billed as standard (the item reports it). 'high' is billed with its own per-minute event.", "default": "standard" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Fields to include in each dataset item: 'text' (full transcript), 'segments' (list with start, end and text per phrase), 'srt' and 'vtt' (subtitle files as strings).", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ] }, "default": [ "text", "segments" ] }, "maxDurationMinutes": { "title": "Max duration per file (minutes)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Audio beyond this length is not transcribed or charged. Files whose header already shows a longer duration are refused. Protects you from unexpectedly long inputs.", "default": 120 } } }, "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 } } } } } } } } } }