{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber (Whisper, SRT/VTT)", "description": "Transcribe audio and video you supply, or public podcast RSS/Atom feed episodes, with Whisper (faster-whisper, int8) running inside the Actor. Plain text, SRT, VTT, and optional approximate word timestamps. No scraped platform video.", "version": "0.1", "x-build-id": "nWOkAy3ktZgBMlZOq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/inn_corp~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-inn_corp-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/inn_corp~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-inn_corp-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/inn_corp~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-inn_corp-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "audioUrls": { "title": "Audio/video URLs", "type": "array", "description": "Direct links to the audio or video files to transcribe. Supply only files you have the right to transcribe: each is fetched with a plain HTTP GET, and the Actor never bypasses logins, paywalls, or DRM.", "items": { "type": "string" } }, "rssFeedUrls": { "title": "Podcast RSS/Atom feed URLs", "type": "array", "description": "Public podcast feed URLs. The Actor parses each feed's (RSS) or (Atom) tags and transcribes up to enclosuresPerFeed episodes per feed, newest first as the feed lists them.", "items": { "type": "string" } }, "enclosuresPerFeed": { "title": "Max episodes per feed", "minimum": 1, "maximum": 25, "type": "integer", "description": "How many enclosure URLs to pull from each RSS/Atom feed and transcribe.", "default": 5 }, "modelSize": { "title": "Whisper model size", "enum": [ "tiny", "base", "small", "large-v3-turbo" ], "type": "string", "description": "Bigger models are more accurate and slower. \"base\" is the default balance; see the README's speed/quality table before changing it for long files. Only \"base\" has a real cloud cost benchmark; \"tiny\", \"small\", and \"large-v3-turbo\" are unverified and may run slower (and cost more at the same per-minute price) than base.", "default": "base" }, "language": { "title": "Language (optional)", "type": "string", "description": "ISO 639-1 code (e.g. \"en\", \"es\", \"fr\"). Leave empty to auto-detect from the first seconds of audio." }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Adds a per-word start/end/probability array to each transcript. This is Whisper's inference-time approximation, not exact forced alignment; it can drift around pauses, cross-talk, and music. Off by default because it costs extra compute and most callers just want segment-level SRT/VTT.", "default": false }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which caption formats to generate alongside the plain-text transcript (always included). SRT and VTT are skipped, saved as null, for formats you don't select.", "items": { "type": "string", "enum": [ "text", "srt", "vtt" ], "enumTitles": [ "Plain text", "SRT", "VTT" ] }, "default": [ "text", "srt", "vtt" ] }, "maxAudioMinutes": { "title": "Max audio/video minutes per source", "minimum": 1, "maximum": 30, "type": "integer", "description": "Duration cap, checked with ffprobe before transcription starts. Apify bills the Actor's operator for compute time, not the caller, so a job that can't finish inside the run timeout would otherwise silently burn money; anything over this cap is rejected with a clean \"too-long\" summary and no charge. Sized against a real cloud benchmark at modelSize=base (measured real-time factor 0.32x, i.e. faster than real time); the 30-minute ceiling and the Actor's 7200s run timeout both carry margin for slower model sizes, which were not separately cloud-benchmarked. See the README.", "default": 15 } } }, "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 } } } } } } } } } }