{ "openapi": "3.0.1", "info": { "title": "Audio Transcriber - Speech-to-Text API", "description": "Transcribe MP3/WAV/FLAC/OGG/WEBM/M4A audio into text with speaker diarization, timestamps, context-aware terminology, and SRT/VTT. No external transcription API key required. Built for batch/API/MCP workflows.", "version": "0.1", "x-build-id": "cHylTK5NovCXEiSf5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automa-flow~audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automa-flow-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automa-flow~audio-transcriber/runs": { "post": { "operationId": "runs-sync-automa-flow-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automa-flow~audio-transcriber/run-sync": { "post": { "operationId": "run-sync-automa-flow-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "audioUrls" ], "properties": { "audioUrls": { "title": "Audio URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "1-100 public HTTPS direct audio file URLs (MP3, WAV, FLAC, OGG, WEBM, M4A, AAC). Exact duplicate URLs are transcribed once and mirrored into every matching Dataset row. Webpage and social-media page URLs are not supported.", "items": { "type": "string", "minLength": 8, "maxLength": 2048, "pattern": "^https://" } }, "diarize": { "title": "Speaker diarization", "type": "boolean", "description": "Label different speakers in the transcript when possible.", "default": true }, "contextBias": { "title": "Context bias terms", "maxItems": 100, "type": "array", "description": "Up to 100 single words that guide the spelling of names and domain terms, for example Armstrong, Voxtral or co-op. No spaces or commas inside an entry: enter a two-word name as two entries. Optimized for English; other languages are experimental.", "items": { "type": "string", "minLength": 1, "maxLength": 100, "pattern": "^[^\\s,]+$" }, "default": [] }, "includeSrt": { "title": "Include SRT", "type": "boolean", "description": "Generate an SRT subtitle track from segment timestamps.", "default": true }, "includeVtt": { "title": "Include VTT", "type": "boolean", "description": "Generate a WebVTT subtitle track from segment timestamps.", "default": true }, "maxDurationSeconds": { "title": "Max duration (seconds)", "minimum": 1, "maximum": 3600, "type": "integer", "description": "Reject files longer than this before calling the transcription provider. Default and maximum are 3600 seconds (60 minutes) until a longer limit is live-verified.", "default": 3600 }, "mistralApiKey": { "title": "Your Mistral API key (optional)", "type": "string", "description": "Leave empty to use the included transcription: nothing to set up, $0.007 per started audio minute. Or paste your own Mistral API key: this Actor then charges $0.004 per started audio minute and Mistral bills your account directly for the transcription. Create a key at console.mistral.ai > API Keys > Create new key. Apify stores it encrypted; it is sent only to api.mistral.ai and never logged or written to the output." }, "payload": { "title": "Integration payload", "type": "object", "description": "Added by an Apify Actor-to-Actor integration. It is accepted so the run can start and is not read or stored. Put the audio links in audioUrls of the integration input." } } }, "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 } } } } } } } } } }