{ "openapi": "3.0.1", "info": { "title": "Speech to Text — YouTube, TikTok, Instagram, 99+ Languages", "description": "Multi-engine speech-to-text for YouTube, TikTok, Instagram, podcasts, X, and direct media URLs. Auto-detects 99+ languages, routes across Groq/OpenAI/ElevenLabs/Google with automatic failover, and returns text, SRT/VTT subtitles, and optional speaker diarization. Pay-per-event — no subscription.", "version": "0.1", "x-build-id": "K7mcvtXzL3Yp2ThMQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/andronixmd~speech-to-text-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-andronixmd-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/andronixmd~speech-to-text-transcriber/runs": { "post": { "operationId": "runs-sync-andronixmd-speech-to-text-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/andronixmd~speech-to-text-transcriber/run-sync": { "post": { "operationId": "run-sync-andronixmd-speech-to-text-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "Audio / video URLs", "type": "array", "description": "YouTube, TikTok, Instagram, podcast, X links — or direct https media file URLs (mp3, wav, m4a, mp4, …). One transcript per URL.", "items": { "type": "string" } }, "language": { "title": "Language hint", "type": "string", "description": "Expected BCP-47 language tag (en, ru, ro, …). Leave empty for auto-detection." }, "timestamps": { "title": "Timestamp granularity", "enum": [ "none", "segment", "word" ], "type": "string", "description": "How finely to time-stamp the transcript: no timestamps, per-segment, or per-word.", "default": "segment" }, "diarize": { "title": "Speaker diarization", "type": "boolean", "description": "Label speakers S1, S2, … (premium engines, higher per-minute rate).", "default": false }, "provider": { "title": "Pin a specific engine (advanced)", "type": "string", "description": "Force one exact engine instead of automatic tier routing + failover — e.g. \"groq/whisper-large-v3\", \"groq/whisper-large-v3-turbo\", \"openai/whisper-1\", \"openai/gpt-4o-mini-transcribe\", \"openai/gpt-4o-transcribe-diarize\", \"elevenlabs/scribe_v2\", \"google/chirp_3\", \"google/gemini\". Only engines whose provider key is configured on this actor are usable. Leave empty for automatic routing (recommended)." }, "summarize": { "title": "Add: transcript summary", "type": "boolean", "description": "Add a 2-4 sentence AI summary of the transcript (billed per item).", "default": false }, "translateTo": { "title": "Add: translate transcript", "type": "string", "description": "BCP-47 code to translate the transcript into (e.g. \"en\", \"es\"). Leave empty to skip (billed per item when set)." }, "extractKeywords": { "title": "Add: extract keywords", "type": "boolean", "description": "Add 5-10 extracted keywords/topics from the transcript (billed per item).", "default": false } } }, "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 } } }, "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 } } } } } } } } } }