{ "openapi": "3.0.1", "info": { "title": "Speech to Text: Whisper Audio & Video Transcriber", "description": "Transcribe audio and video to text with faster-whisper running inside Apify. Get language detection, word timestamps, SRT/VTT/TXT exports, and reliable batch processing with per-file error handling—no API key needed.", "version": "1.0", "x-build-id": "yG5wvcVNiJsfDmDhK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lightning_ak~speech-to-text-whisper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lightning_ak-speech-to-text-whisper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lightning_ak~speech-to-text-whisper/runs": { "post": { "operationId": "runs-sync-lightning_ak-speech-to-text-whisper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lightning_ak~speech-to-text-whisper/run-sync": { "post": { "operationId": "run-sync-lightning_ak-speech-to-text-whisper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or video URLs", "maxItems": 50, "type": "array", "description": "Direct links to mp3, wav, m4a, mp4, webm, ogg, flac, and similar media files. YouTube, Vimeo, SoundCloud, and other supported pages are also accepted.", "items": { "type": "string" } }, "audioFiles": { "title": "Uploaded audio files", "maxItems": 50, "type": "array", "description": "Upload files here (they are stored in a key-value store) or paste key-value store record keys/URLs. Files larger than the configured limit (1 GB by default) are rejected.", "items": { "type": "string" } }, "modelSize": { "title": "Whisper model", "enum": [ "tiny", "base", "small", "medium", "large-v3" ], "type": "string", "description": "Larger models are more accurate but slower. The Docker image bakes in the 'base' model by default; other sizes download on first use unless the image is rebuilt with a different WHISPER_MODEL build arg. Billing uses audio-minute-basic for tiny/base, audio-minute-small for small, audio-minute-medium for medium, and audio-minute-large for large-v3.", "default": "base" }, "language": { "title": "Language", "pattern": "^(auto|[a-zA-Z]{2,3})$", "type": "string", "description": "ISO 639-1/2 code such as en, de, es, or zh, or 'auto' to detect the language automatically.", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe keeps the original language. Translate always produces English text.", "default": "transcribe" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Transcript files are saved to the default key-value store with the transcripts- key prefix and linked from every dataset item. The dataset always contains the full JSON result.", "items": { "type": "string", "enum": [ "json", "txt", "srt", "vtt" ], "enumTitles": [ "JSON (full result)", "Plain text", "SRT subtitles", "WebVTT subtitles" ] } }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add a word array with start/end times to every segment. Slower than segment-only timestamps.", "default": false }, "vadFilter": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Use voice activity detection to skip silence and speed up long recordings. Disable it to force processing of the entire timeline; silent stretches may produce hallucinated text.", "default": true }, "maxConcurrency": { "title": "Maximum concurrent transcriptions", "minimum": 0, "maximum": 8, "type": "integer", "description": "0 selects a safe value automatically from allocated memory and CPU. Higher values can improve throughput but use more RAM; the Actor clamps the value to a safe limit.", "default": 0 }, "beamSize": { "title": "Beam size", "minimum": 1, "maximum": 10, "type": "integer", "description": "Beam search width. 5 is a good default; 1 is greedy and fastest.", "default": 5 }, "temperature": { "title": "Temperature", "minimum": 0, "maximum": 1, "type": "number", "description": "Sampling temperature. 0 (recommended) uses Whisper's standard fallback ladder (0.0, 0.2, ... 1.0) to recover from repetition and decoding failures.", "default": 0 }, "initialPrompt": { "title": "Initial prompt", "maxLength": 2000, "type": "string", "description": "Optional context for the model, such as names, terminology, or a list of expected words. Keep it short." } } }, "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 } } } } } } } } } }