{ "openapi": "3.0.1", "info": { "title": "Audio to Text — Whisper Transcription, SRT, RAG Chunks", "description": "Transcribe audio and video files, Drive or Dropbox links and podcast feeds with Whisper. Timestamped text, SRT and VTT subtitles, Markdown and RAG chunks in 99 languages. Failed files are free.", "version": "0.0", "x-build-id": "1DPFyVT9fjQwyL0a6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saliga~audio-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saliga-audio-to-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/saliga~audio-to-text/runs": { "post": { "operationId": "runs-sync-saliga-audio-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/saliga~audio-to-text/run-sync": { "post": { "operationId": "run-sync-saliga-audio-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Audio or video links", "type": "array", "description": "Direct links to audio or video files (mp3, m4a, aac, wav, ogg, opus, flac, mp4, mov, webm, mkv), or Google Drive and Dropbox share links. One result per file. YouTube, TikTok and other platform pages are not supported: use a link to the file itself.", "items": { "type": "string" } }, "podcastFeeds": { "title": "Podcast feeds (RSS)", "type": "array", "description": "Podcast RSS or Atom feed URLs. The newest episodes of each feed are transcribed, with their title and date.", "items": { "type": "string" } }, "episodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many of the newest episodes to transcribe from each feed.", "default": 1 }, "model": { "title": "Model", "enum": [ "base", "small" ], "type": "string", "description": "Base: fast and cheap, good for clear speech in common languages. Small: more accurate with names, accents, noisy recordings and less common languages; about 3 times slower and priced higher.", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "Two-letter code of the spoken language (en, es, de, fr, pt, tr, ja, ...), or auto to detect it. Setting it helps with short files and with speakers who mix languages.", "default": "auto" }, "task": { "title": "Output language", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe: text in the spoken language. Translate: English text from speech in any language.", "default": "transcribe" }, "wordTimestamps": { "title": "Word timestamps", "type": "boolean", "description": "Add start and end times for every word inside each segment (karaoke-style captions, precise search). A little slower.", "default": false }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 300, "type": "integer", "description": "Only the first this many minutes of each file are transcribed and charged. Longer files are marked truncated.", "default": 180 }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Also return the transcript split into chunks of about this many characters (0 = off). Chunks are made of whole sentences and keep their time range, so search results can link to the right moment. Try 1500.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "The last sentences of a chunk, up to this many characters, are repeated at the start of the next one (at most half the chunk size).", "default": 200 }, "saveFiles": { "title": "Save SRT, VTT, Markdown and text files", "type": "boolean", "description": "Also save each transcript as .srt, .vtt, .md and .txt files in the run's key-value store, with download links in the result.", "default": true }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Files larger than this are skipped with an error (not charged). Video files are large: the audio track is read from them.", "default": 500 }, "requestHeaders": { "title": "Request headers", "type": "object", "description": "Extra HTTP headers for downloading, for example {\"Authorization\": \"Bearer …\"} for files behind a token. Sent only to the host of each URL you gave, never to a redirect on another host. They are stored with the run input, so prefer short-lived tokens or pre-signed URLs." } } }, "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 } } } } } } } } } }