{ "openapi": "3.0.1", "info": { "title": "Audio to Text Transcriber with Subtitles", "description": "Speech to text for audio files: transcribe MP3, WAV, FLAC and OGG to text with timestamps and SRT/VTT subtitles. 40+ languages, translation to English, private on-server speech models. Silent files are free.", "version": "0.0", "x-build-id": "MMEzj7Aops1Ux8oSe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ridgeline_apps~audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ridgeline_apps-audio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ridgeline_apps~audio-transcriber/runs": { "post": { "operationId": "runs-sync-ridgeline_apps-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ridgeline_apps~audio-transcriber/run-sync": { "post": { "operationId": "run-sync-ridgeline_apps-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "files" ], "properties": { "files": { "title": "Audio files", "type": "array", "description": "Paste audio file URLs (one per line) or upload files. Supports MP3, WAV, FLAC and OGG (Vorbis). M4A, AAC, Opus and video files are not supported: convert them to MP3 first." }, "accuracy": { "title": "Accuracy", "enum": [ "standard", "high" ], "type": "string", "description": "Standard is fast and works well for clear speech. High accuracy uses a larger model: better with accents, noise and less common words, about 3x slower and priced higher.", "default": "standard" }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "es", "fr", "de", "pt", "it", "nl", "pl", "ru", "uk", "tr", "ar", "hi", "ja", "ko", "zh", "id", "vi", "th", "ms", "tl", "sv", "da", "no", "fi", "cs", "sk", "ro", "hu", "el", "he", "fa", "ur", "bn", "ta", "ca", "hr", "sr", "bg", "lt", "sl", "sw" ], "type": "string", "description": "Pick the language spoken in the audio, or leave Auto-detect. Setting it improves accuracy for short or noisy files.", "default": "auto" }, "task": { "title": "Output", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe keeps the original language. Translate produces an English transcript from any supported language.", "default": "transcribe" }, "includeSubtitles": { "title": "Include SRT and VTT subtitles", "type": "boolean", "description": "Add ready-to-use subtitle text in SRT and WebVTT formats to each result.", "default": true }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add the transcript as a list of segments with start and end times in seconds.", "default": true }, "includeWordTimestamps": { "title": "Include word timestamps", "type": "boolean", "description": "Add the start and end time and confidence of every word. Slightly slower.", "default": false }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 200 }, "maxMinutesPerFile": { "title": "Max audio length per file (minutes)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer files are skipped and not charged. Long files also need a longer run timeout: plan about 1 minute of run time per 8 minutes of audio on Standard (4 GB memory).", "default": 180 } } }, "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 } } } } } } } } } }