{ "openapi": "3.0.1", "info": { "title": "Speech to Text from Links: MP3, MP4, Google Drive, Podcast RSS", "description": "Transcribe audio and video files from public links: MP3, M4A, WAV, MP4, MOV and more, Google Drive and Dropbox share links, podcast RSS feeds and Apple Podcasts. Full text, timestamped segments, SRT and VTT subtitles, 99 languages auto-detected. Pay only per transcribed minute.", "version": "0.1", "x-build-id": "D7mSrBIiROe4AIbb4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neverempty~speech-to-text-from-links/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neverempty-speech-to-text-from-links", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neverempty~speech-to-text-from-links/runs": { "post": { "operationId": "runs-sync-neverempty-speech-to-text-from-links", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neverempty~speech-to-text-from-links/run-sync": { "post": { "operationId": "run-sync-neverempty-speech-to-text-from-links", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 file links", "type": "array", "description": "Public links to audio or video files: direct links (MP3, M4A, WAV, OGG, OPUS, FLAC, MP4, MOV, WEBM, MKV and more), Google Drive or Dropbox share links (\"Anyone with the link\"), or a podcast RSS feed / Apple Podcasts page. One transcript row per file. Links to YouTube, TikTok, Instagram and other video platforms are not downloaded.", "items": { "type": "string" } }, "podcastFeeds": { "title": "Podcast feeds", "type": "array", "description": "Optional. A podcast RSS feed address or an Apple Podcasts show or episode link. The newest episodes are transcribed (see \"Episodes per feed\").", "items": { "type": "string" } }, "accuracy": { "title": "Accuracy", "enum": [ "fast", "accurate" ], "type": "string", "description": "\"Fast\" uses the Whisper base model: quick and the lowest price, good for clear English speech. \"Accurate\" uses the larger Whisper small model: fewer wrong words (especially names, numbers and non-English speech), takes about 3 times longer, and is charged at the \"accurate\" price per minute.", "default": "fast" }, "maxEpisodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many of the newest episodes to transcribe from each podcast feed.", "default": 3 }, "onlyNewEpisodes": { "title": "Only episodes not transcribed before", "type": "boolean", "description": "For scheduled runs: skip episodes this account already transcribed from the same feed, so each episode is transcribed and charged once.", "default": false }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "tr", "pl", "ca", "nl", "ar", "sv", "it", "id", "hi", "fi", "vi", "he", "uk", "el", "ms", "cs", "ro", "da", "hu", "ta", "no", "th", "ur", "hr", "bg", "lt", "la", "mi", "ml", "cy", "sk", "te", "fa", "lv", "bn", "sr", "az", "sl", "kn", "et", "mk", "br", "eu", "is", "hy", "ne", "mn", "bs", "kk", "sq", "sw", "gl", "mr", "pa", "si", "km", "sn", "yo", "so", "af", "oc", "ka", "be", "tg", "sd", "gu", "am", "yi", "lo", "uz", "fo", "ht", "ps", "tk", "nn", "mt", "sa", "lb", "my", "bo", "tl", "mg", "as", "tt", "haw", "ln", "ha", "ba", "jw", "su" ], "type": "string", "description": "Leave on \"Detect automatically\" unless you know the language; setting it can help with short or noisy recordings.", "default": "auto" }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 240, "type": "integer", "description": "Longer files are skipped with a \"too_long\" row and are not charged.", "default": 120 }, "maxTotalMinutes": { "title": "Max total minutes per run", "minimum": 1, "maximum": 3000, "type": "integer", "description": "A cap on the audio minutes charged in one run. Files that would go over it get a \"run_limit\" row and are not charged. The default 300 fits in the default 6-hour run timeout; if you raise this, also raise \"Timeout\" in the run options (files that cannot finish before the timeout get a \"time_limit\" row and are not charged).", "default": 300 }, "apiKey": { "title": "Your OpenAI or Groq API key", "type": "string", "description": "Optional. An OpenAI key (starts with \"sk-\", uses whisper-1) or a Groq key (starts with \"gsk_\", uses whisper-large-v3-turbo, or whisper-large-v3 when Accuracy is \"Accurate\"). The key is stored encrypted, is sent only to that provider, and is never written to the results or the log." } } }, "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 } } } } } } } } } }