{ "openapi": "3.0.1", "info": { "title": "Video & Audio Transcriber · Whisper Speech-to-Text", "description": "Transcribe any video or audio URL to text with Whisper running inside the Actor — no API key. TikTok, YouTube, Instagram, Facebook, X, Rumble, podcast RSS feeds & direct files. Full text, timestamped segments, SRT + VTT subtitles, 99+ languages auto-detected. One flat rate for video and audio.", "version": "0.0", "x-build-id": "ALe1N4sR35DEsZ9IW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~video-audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-video-audio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~video-audio-transcriber/runs": { "post": { "operationId": "runs-sync-memo23-video-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~video-audio-transcriber/run-sync": { "post": { "operationId": "run-sync-memo23-video-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "minItems": 1, "maxItems": 50, "type": "array", "description": "Video, audio, podcast or direct-file URLs to transcribe. Works with TikTok, YouTube, Instagram, Facebook, X (Twitter), Rumble, SoundCloud, Vimeo, Twitch and 1800+ other sites, podcast RSS feeds (episodes are expanded automatically) and direct media links (mp3, mp4, wav, m4a, flac, …). Audio is extracted from video automatically.", "items": { "type": "string" } }, "language": { "title": "Language (optional)", "type": "string", "description": "ISO 639-1 code of the spoken language (e.g. 'en', 'es', 'pt', 'de'). Leave empty to auto-detect — Whisper recognizes 99+ languages.", "default": "" }, "model": { "title": "Whisper model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Accuracy vs. speed trade-off. 'base' (default) is fast and accurate on clear speech, 'small' is the most accurate for hard audio, 'tiny' is fastest. All three are baked into the Actor image — no downloads at run time.", "default": "base" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Instead of transcribing in the original language, output an English translation of the speech (Whisper's built-in translate task). SRT/VTT subtitles are translated too.", "default": false }, "maxMinutesPerItem": { "title": "Max minutes per item", "minimum": 1, "maximum": 600, "type": "integer", "description": "Safety cap on how many minutes of media to transcribe per URL. Longer items are transcribed up to this cap and billed only for the transcribed minutes.", "default": 120 }, "maxEpisodesPerFeed": { "title": "Max episodes per podcast feed", "minimum": 1, "maximum": 50, "type": "integer", "description": "When a URL is a podcast RSS/Atom feed, transcribe this many of the newest episodes (each episode becomes one output item).", "default": 1 }, "cookies": { "title": "Cookies (optional)", "type": "string", "description": "Contents of a Netscape cookies.txt exported from a logged-in browser session. Useful for YouTube (avoids the 'Sign in to confirm you're not a bot' gate) and for age/region-restricted content on any network. Leave empty for public content and direct files." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxy by default — social networks (YouTube, TikTok, Instagram, …) block datacenter IPs when downloading media. Podcast feeds and direct media files are fetched without a proxy automatically, so residential bandwidth is only spent where it is needed.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }