{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcription — Speech to Text, SRT & Summary", "description": "Transcribe audio and video to text: MP3, MP4, WAV, Google Drive, Dropbox and podcasts. Get speaker labels, SRT/VTT subtitles and an AI summary in 99 languages. Fast, accurate speech to text at $0.30 per hour. Failed files are free.", "version": "0.0", "x-build-id": "U4Ab5ZDkSxKewZwwT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/phronexusai~audio-video-transcription/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-phronexusai-audio-video-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/phronexusai~audio-video-transcription/runs": { "post": { "operationId": "runs-sync-phronexusai-audio-video-transcription", "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/phronexusai~audio-video-transcription/run-sync": { "post": { "operationId": "run-sync-phronexusai-audio-video-transcription", "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": { "audioUrls": { "title": "Audio / video links", "type": "array", "description": "Public links to audio or video files: MP3, WAV, M4A, AAC, OGG, OPUS, FLAC, MP4, MOV, WEBM, MKV and more. Google Drive, Dropbox and OneDrive share links work too (the file must be shared as \"Anyone with the link\"). YouTube, TikTok, Instagram and Spotify page links are not supported.", "items": { "type": "string" } }, "podcastFeeds": { "title": "Podcast feeds", "type": "array", "description": "Podcast RSS feed URLs or Apple Podcasts links. The newest episodes are transcribed.", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Episodes per podcast", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many of the newest episodes to transcribe from each podcast feed.", "default": 3 }, "languageCode": { "title": "Language", "enum": [ "auto", "en", "es", "fr", "de", "it", "pt", "nl", "pl", "ru", "uk", "tr", "ar", "hi", "ja", "ko", "zh", "sv", "da", "no", "fi", "cs", "ro", "el", "hu", "bg", "hr", "sr", "sk", "vi", "id" ], "type": "string", "description": "Leave on \"Detect automatically\" unless you know the language. Setting it can improve accuracy.", "default": "auto" }, "speakerLabels": { "title": "Identify speakers", "type": "boolean", "description": "Label who is speaking (Speaker A, Speaker B, ...) in the transcript and subtitles.", "default": true }, "generateSummary": { "title": "AI summary", "type": "boolean", "description": "Add a short summary, key points and topics for each file. Included in the price.", "default": true }, "outputFormats": { "title": "Output files", "type": "array", "description": "Files saved for each recording (download links are in the results). The transcript text is always in the results table.", "items": { "type": "string", "enum": [ "txt", "srt", "vtt", "md", "json" ], "enumTitles": [ "Plain text (.txt)", "SRT subtitles (.srt)", "WebVTT subtitles (.vtt)", "Markdown with timestamps (.md)", "Full JSON with words and timings (.json)" ] }, "default": [ "txt", "srt", "vtt", "md" ] }, "charsPerCaption": { "title": "Max characters per subtitle line", "minimum": 20, "maximum": 100, "type": "integer", "description": "Longer captions are split. 42 is the common standard for video subtitles.", "default": 42 }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Only the first N minutes of each file are transcribed and charged. Protects you from unexpectedly long files.", "default": 300 }, "maxConcurrency": { "title": "Files in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many files are processed at the same time.", "default": 3 } } }, "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 } } } } } } } } } }