{ "openapi": "3.0.1", "info": { "title": "Audio & Video to Text - Whisper Transcription API", "description": "Transcribe audio and video files from direct URLs (mp3, wav, m4a, ogg, mp4, mov, webm) with Whisper large-v3-turbo. Get text, SRT, VTT, timestamped segments and RAG chunks. $0.004 per audio minute, platform usage included.", "version": "0.1", "x-build-id": "35uhaxQvsy9XQtlR0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zenomastro~audio-video-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zenomastro-audio-video-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/zenomastro~audio-video-to-text/runs": { "post": { "operationId": "runs-sync-zenomastro-audio-video-to-text", "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/zenomastro~audio-video-to-text/run-sync": { "post": { "operationId": "run-sync-zenomastro-audio-video-to-text", "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": "Audio or video file URLs", "maxItems": 500, "type": "array", "description": "Direct links to audio or video files, one per line (mp3, wav, m4a, ogg, opus, flac, webm, mp4, mov, mkv). Links must be public and point straight to the file. YouTube and social-media page links are not supported; use the YouTube Transcript Actor for those.", "default": [ "https://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg" ], "items": { "type": "string" } }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "it", "es", "fr", "de", "pt", "nl", "pl", "ru", "uk", "tr", "ar", "he", "hi", "bn", "ur", "fa", "zh", "ja", "ko", "vi", "th", "id", "ms", "sv", "no", "da", "fi", "cs", "sk", "hu", "ro", "bg", "el", "hr", "sr", "ca", "lt", "lv", "et", "sl", "sw", "af", "ta", "te" ], "type": "string", "description": "Language spoken in the audio. Auto-detect works well for most recordings; choosing the language explicitly can improve accuracy and avoids wrong detection on short or noisy clips.", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe keeps the original language. Translate to English returns the transcript translated into English.", "default": "transcribe" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "What to include in each result row. SRT and VTT subtitles are also saved as files in the key-value store of the run, with direct links. RAG chunks split the transcript into timestamped pieces for embeddings.", "items": { "type": "string", "enum": [ "text", "srt", "vtt", "segments", "chunks" ], "enumTitles": [ "Plain text", "SRT subtitles", "WebVTT subtitles", "Timestamped segments", "RAG chunks" ] }, "default": [ "text", "srt" ] }, "chunkSizeChars": { "title": "RAG chunk size (characters)", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Maximum characters per chunk when the RAG chunks format is selected. Chunks follow segment boundaries and keep start and end times.", "default": 1000 }, "maxDurationMinutes": { "title": "Maximum duration per file (minutes)", "minimum": 1, "maximum": 180, "type": "integer", "description": "Files longer than this are reported as TOO_LONG and are not charged. The hard cap is 180 minutes per file.", "default": 60 }, "maxConcurrency": { "title": "Parallel transcriptions", "minimum": 1, "maximum": 4, "type": "integer", "description": "How many files are processed, and how many audio parts are transcribed, at the same time. Lower values are gentler on the transcription service.", "default": 2 }, "vadFilter": { "title": "Skip silence (voice activity detection)", "type": "boolean", "description": "Remove silent and non-speech sections before transcribing. Helps with long pauses, music or background noise, where the model can otherwise invent text.", "default": false }, "initialPrompt": { "title": "Context prompt", "type": "string", "description": "Optional text that helps the model with names, product terms or spelling, for example a list of speaker names or technical vocabulary. Maximum 800 characters." } } }, "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 } } } } } } } } } }