{ "openapi": "3.0.1", "info": { "title": "Speech to Text: Video & Audio Transcription from any URL", "description": "Transcribe videos and audio to text or timestamped segments by URL: X (Twitter), TikTok, YouTube, LinkedIn, Loom, TED, SoundCloud, Dailymotion, Twitch and 1,000+ sites, playlists and channels, or any audio or video file. Whisper runs inside the run, in about 100 languages; long videos in full.", "version": "0.1", "x-build-id": "GFApTfbJrjq7OUdQG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pikoulas~video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pikoulas-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pikoulas~video-transcriber/runs": { "post": { "operationId": "runs-sync-pikoulas-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pikoulas~video-transcriber/run-sync": { "post": { "operationId": "run-sync-pikoulas-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Video or audio URLs", "type": "array", "description": "Pages of videos or audio (x.com/.../status/..., tiktok.com, youtube.com, linkedin.com/posts/..., loom.com/share/..., ted.com, soundcloud.com, dailymotion.com, twitch.tv clips, and 1,000+ other sites), playlists and channels, or direct links to audio or video files (.mp3, .m4a, .mp4, .wav...).", "items": { "type": "string" } }, "maxVideosPerUrl": { "title": "Max videos per playlist or channel", "minimum": 1, "type": "integer", "description": "Videos taken from each playlist, channel or profile URL, in the site's order. A single video's URL is always one.", "default": 10 }, "maxMinutesPerVideo": { "title": "Max minutes per video", "minimum": 1, "type": "integer", "description": "Transcribes only each video's first minutes, and charges only those. Empty: whole videos." }, "model": { "title": "Speech-to-text model", "enum": [ "base", "small" ], "type": "string", "description": "Whisper base is fast and good on clear speech. Whisper small is more accurate on accents, crosstalk, names and languages other than English, takes about three times as long and costs $0.008 per started minute against base's $0.003 ($0.016 and $0.006 on Apify's free plan).", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "The language spoken, as a code (en, es, pt, de, hi...), when all the videos share one. Empty: detected for each video.", "default": "" }, "includeTimestamps": { "title": "Include timestamps", "type": "boolean", "description": "Adds the transcript as segments with their start and end in seconds, next to the plain text.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed for most runs: a site that refuses Apify's servers is switched to Apify's residential proxy by itself, its traffic charged as its own event.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }