{ "openapi": "3.0.1", "info": { "title": "Audio & Video to Text - Whisper Speech-to-Text Transcriber", "description": "Transcribe audio and video files from URLs to text with OpenAI Whisper (faster-whisper): podcasts, interviews, meetings, voice notes. 99 languages with auto-detect, timestamped segments, SRT and WebVTT subtitles, optional translation to English. No API key, no external AI service.", "version": "1.1", "x-build-id": "Stz8mpa627b4cNwmq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/teddythebuilder~speech-to-text-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-teddythebuilder-speech-to-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/teddythebuilder~speech-to-text-transcriber/runs": { "post": { "operationId": "runs-sync-teddythebuilder-speech-to-text-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/teddythebuilder~speech-to-text-transcriber/run-sync": { "post": { "operationId": "run-sync-teddythebuilder-speech-to-text-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "audioUrls": { "title": "Audio / video file URLs", "type": "array", "description": "Direct links to audio or video files (MP3, M4A, WAV, OGG, FLAC, MP4, WebM, MOV, MKV...). One URL per line. Podcast RSS enclosures work too. Web pages and YouTube links are not supported.", "default": [ "https://raw.githubusercontent.com/ggerganov/whisper.cpp/master/samples/jfk.wav" ], "items": { "type": "string" } }, "podcastFeedUrls": { "title": "Podcast RSS feed URLs", "type": "array", "description": "Transcribe the latest episodes of podcasts: give the RSS feed URL (find it on the podcast's website or in Apple Podcasts via the show's page) and the episode audio files are found automatically.", "default": [], "items": { "type": "string" } }, "episodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many of the newest episodes to transcribe from each podcast feed.", "default": 3 }, "datasetId": { "title": "Dataset ID with file URLs", "type": "string", "description": "Read audio/video URLs from another Apify dataset, e.g. the output of the Bulk Image & File Downloader (field fileUrl) or a podcast scraper." }, "datasetUrlField": { "title": "URL field", "type": "string", "description": "Field in the dataset items that holds the audio/video URL, e.g. fileUrl, audioUrl, url.", "default": "url" }, "model": { "title": "Model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Base is a good default for clear speech. Small is noticeably more accurate (names, accents, noise) but slower, so it is billed at a higher rate. Tiny is fastest and least accurate.", "default": "base" }, "language": { "title": "Spoken language", "type": "string", "description": "Two-letter code such as en, sv, de, fr, es, ja. Leave empty to detect it automatically from the first 30 seconds." }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Output an English translation instead of a transcript in the spoken language.", "default": false }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add a segments array with start/end seconds and text for every phrase.", "default": true }, "includeSubtitles": { "title": "Include SRT and WebVTT subtitles", "type": "boolean", "description": "Add ready-to-use srt and vtt strings.", "default": false }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add start/end time for every word (a little slower).", "default": false }, "skipSilence": { "title": "Skip silence", "type": "boolean", "description": "Voice-activity detection removes long silences and music-only parts, which avoids made-up text and speeds things up. Billing still uses the full file length.", "default": true }, "maxMinutesTotal": { "title": "Max audio minutes per run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop starting new files once this many audio minutes were transcribed. You pay per minute of audio.", "default": 60 }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 0, "type": "integer", "description": "Longer files are skipped for free (set 0 to allow any length).", "default": 180 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Larger downloads are skipped for free.", "default": 300 } } }, "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 } } } } } } } } } }