{ "openapi": "3.0.1", "info": { "title": "Universal Media Transcriber · Whisper Speech-to-Text", "description": "Transcribe audio & video from any URL — YouTube, podcasts, direct files and hundreds of sites — with Whisper. Get text, timestamped segments, SRT and VTT. 90+ languages, no API key.", "version": "1.0", "x-build-id": "JTgvXI8TdhRe85mZu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sauliusautomatesit~media-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sauliusautomatesit-media-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sauliusautomatesit~media-transcriber/runs": { "post": { "operationId": "runs-sync-sauliusautomatesit-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sauliusautomatesit~media-transcriber/run-sync": { "post": { "operationId": "run-sync-sauliusautomatesit-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs of audio or video to transcribe. Works with YouTube, podcast episodes, direct audio/video files (mp3, mp4, wav, m4a…), and hundreds of other sites supported by yt-dlp.", "items": { "type": "string" } }, "model": { "title": "Whisper model", "enum": [ "tiny", "base", "small", "medium" ], "type": "string", "description": "Accuracy vs speed/cost. `tiny`/`base` are fast and cheap; `small`/`medium` are more accurate but slower (and cost more per minute of audio). `base` is a great default. (`small`/`medium` download on first use.)", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code of the audio (e.g. `en`, `es`, `fr`, `de`, `hi`). Leave blank to auto-detect. Whisper supports 90+ languages." }, "translate": { "title": "Translate to English", "type": "boolean", "description": "Translate the speech to English instead of transcribing in the original language.", "default": false }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which transcript formats to include per item. `text` = full plain text; `segments` = timestamped chunks; `srt`/`vtt` = subtitle files.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments" ] }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Also produce per-word timestamps inside each segment (useful for captions/karaoke). Slightly slower.", "default": false }, "maxDurationMinutes": { "title": "Max duration per item (minutes)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Skip media longer than this (protects against accidental huge/expensive runs).", "default": 180 }, "beamSize": { "title": "Beam size", "minimum": 1, "maximum": 5, "type": "integer", "description": "Decoding beam size. 1 = fastest (greedy); higher = slightly more accurate but slower.", "default": 1 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy for downloading the media (helps with rate-limited or geo-restricted sources like YouTube).", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }