{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber - Speech to Text, SRT & Timestamps", "description": "Transcribe audio and video to text with Whisper inside the Actor - no API key. Any direct media URL. Returns text, timestamped segments, SRT/VTT subtitles and optional RAG chunks. Built for long recordings: repetition loops and silence hallucinations are repaired. Billed per minute of speech.", "version": "0.1", "x-build-id": "mNM2AmTSXtbJkPEt7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/readable_slash~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-readable_slash-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/readable_slash~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-readable_slash-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/readable_slash~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-readable_slash-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 URLs", "type": "array", "description": "Direct links to audio or video files, or podcast episode enclosures. Supports mp3, m4a, wav, flac, ogg, opus, aac, mp4, webm, mkv, mov and other common formats. This Actor does not download from YouTube, TikTok, Instagram or similar platforms - supply media you can link to directly.", "items": { "type": "string" } }, "model": { "title": "Model size", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Larger models are more accurate on difficult audio (accents, noise, crosstalk) and cost slightly more compute. 'base' is the balanced default and handles clear speech well.", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "ISO code such as en, nl, de, fr, es. Leave empty to detect automatically. Setting it explicitly is faster and more reliable when you already know the language." }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which renderings to include in each result row.", "items": { "type": "string", "enum": [ "text", "paragraphs", "srt", "vtt" ], "enumTitles": [ "Plain text", "Paragraphs (split at natural pauses)", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text" ] }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Return every recognised span with its start and end time.", "default": true }, "chunkForRag": { "title": "Also return RAG chunks", "type": "boolean", "description": "Group the transcript into retrieval-ready chunks that never split a sentence and carry the timestamp of what was said, so a search hit can be cited or played back at the exact second.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Soft ceiling per chunk.", "default": 1200 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Characters repeated between neighbouring chunks so a fact spanning a boundary stays retrievable.", "default": 120 }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 0, "maximum": 600, "type": "integer", "description": "Stop after this many minutes of each recording. 0 means no limit. Useful as a cost ceiling when processing files of unknown length.", "default": 0 } } }, "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 } } } } } } } } } }