{ "openapi": "3.0.1", "info": { "title": "AI Voice Generator & Cloner — 646-language TTS + cloning", "description": "Text to speech and voice cloning over HTTP. Design a voice (gender/age/pitch/accent) or clone one from a short sample, in 646 languages. Returns a WAV URL. Pay per request + per 1000 characters.", "version": "0.1", "x-build-id": "5qrhggs68zKsTjupI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/synthetic.ia~ai-voice-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-synthetic.ia-ai-voice-generator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/synthetic.ia~ai-voice-generator/runs": { "post": { "operationId": "runs-sync-synthetic.ia-ai-voice-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/synthetic.ia~ai-voice-generator/run-sync": { "post": { "operationId": "run-sync-synthetic.ia-ai-voice-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "text" ], "properties": { "mode": { "title": "Mode", "enum": [ "design", "clone" ], "type": "string", "description": "Design a voice from scratch, or clone one from a reference sample.", "default": "design" }, "text": { "title": "Text to speak", "type": "string", "description": "What the voice should say (max 5000 characters). Supports expressive tags like [laughter], [sigh], [surprise-ah].", "default": "Hola, esta voz fue generada con inteligencia artificial en Apify." }, "language": { "title": "Language", "type": "string", "description": "ISO code (es, en, ja, it, pt…) or English name. 646 languages supported.", "default": "es" }, "gender": { "title": "Gender (design)", "enum": [ "female", "male" ], "type": "string", "description": "Design mode only.", "default": "male" }, "age": { "title": "Age (design)", "enum": [ "child", "teenager", "young_adult", "middle_aged", "elderly" ], "type": "string", "description": "Design mode only.", "default": "middle_aged" }, "pitch": { "title": "Pitch (design)", "enum": [ "very_low", "low", "moderate", "high", "very_high" ], "type": "string", "description": "Design mode only.", "default": "low" }, "whisper": { "title": "Whisper / ASMR (design)", "type": "boolean", "description": "Design mode only. Whispered, breathy delivery.", "default": false }, "accent": { "title": "Accent (design, English)", "type": "string", "description": "Design mode only, English voices: american, british, australian, indian…" }, "referenceAudioUrl": { "title": "Reference audio URL (clone)", "type": "string", "description": "Clone mode: direct http(s) URL to ~10s+ of clean speech (WAV/MP3, max 12 MB)." }, "referenceText": { "title": "Reference transcript (clone)", "type": "string", "description": "Clone mode: transcript of the reference audio (optional; improves the clone)." }, "rightsConfirmed": { "title": "I have the right to clone this voice", "type": "boolean", "description": "Clone mode: you confirm you own this voice or are authorized to use it. Required to clone.", "default": false }, "quality": { "title": "Quality", "enum": [ "fast", "balanced", "high" ], "type": "string", "description": "Higher quality uses more inference steps.", "default": "high" }, "speed": { "title": "Speed", "minimum": 0.5, "maximum": 2, "type": "number", "description": "0.5 (slow) to 2.0 (fast).", "default": 1 } } }, "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 } } } } } } } } } }