{ "openapi": "3.0.1", "info": { "title": "Text to Speech API — Batch, 30+ Languages, Pay per Character", "description": "Text-to-speech (TTS) API: turn one or many texts into MP3 or WAV voiceover files and get, for each text, a dataset item with the audio URL, duration and character count. English, French, Spanish, German and 30+ languages, auto-detected. No API key, pay per character.", "version": "0.1", "x-build-id": "a2eYBiwrN76edqjvt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sherwood~text-to-speech-batch/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sherwood-text-to-speech-batch", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sherwood~text-to-speech-batch/runs": { "post": { "operationId": "runs-sync-sherwood-text-to-speech-batch", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sherwood~text-to-speech-batch/run-sync": { "post": { "operationId": "run-sync-sherwood-text-to-speech-batch", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "texts": { "title": "Texts", "type": "array", "description": "Texts to turn into speech, as a list, up to 5,000 characters each. One dataset item is returned per text, with an index matching the input order. For a single text, use text instead. Aliases merged into this list: text, prompts, prompt, sentences.", "default": [ "Welcome to our store. Your order has shipped and should arrive within three business days.", "Bienvenue dans notre boutique. Votre commande a été expédiée et arrivera sous trois jours ouvrés." ], "items": { "type": "string" } }, "text": { "title": "Single text (alias)", "type": "string", "description": "A single text, voiced as one audio file. Merged with texts." }, "prompts": { "title": "prompts (alias)", "type": "array", "description": "Alias of texts.", "items": { "type": "string" } }, "sentences": { "title": "sentences (alias)", "type": "array", "description": "Alias of texts.", "items": { "type": "string" } }, "language": { "title": "Language", "enum": [ "auto", "english", "french", "spanish", "german", "italian", "portuguese", "dutch", "polish", "russian", "turkish", "arabic", "hindi", "japanese", "korean", "chinese", "indonesian", "vietnamese", "thai", "swedish", "danish", "norwegian", "finnish", "greek", "czech", "romanian", "hungarian", "ukrainian", "bulgarian", "catalan", "croatian", "slovak", "slovenian", "hebrew", "malay", "afrikaans", "cantonese" ], "type": "string", "description": "Language of the texts: auto detects it per text (recommended for mixed batches), or force one of 36 languages. English uses the fast model by default; every other language uses the premium multilingual model. Malay and Cantonese must be forced; a detected language outside the list is voiced by the premium model with its own detection.", "default": "auto" }, "voice": { "title": "Voice", "type": "string", "description": "female or male picks a natural default voice for the model in use. You can also pass an explicit voice id: Kokoro ids (af_heart, af_bella, am_michael, am_adam…) for English standard quality, MiniMax ids (Wise_Woman, Calm_Woman, Friendly_Person, Deep_Voice_Man, Patient_Man, Casual_Guy, Lively_Girl, Elegant_Man…) for premium.", "default": "female" }, "quality": { "title": "Quality", "enum": [ "standard", "premium" ], "type": "string", "description": "standard: Kokoro, fast and cheap, English only (other languages are automatically switched to premium). premium: MiniMax Speech 2.8, natural voices in 30+ languages, supports pauses like <#1.5#> and tags like (laughs).", "default": "standard" }, "speed": { "title": "Speed", "type": "string", "description": "Speech speed multiplier, 0.5 to 2.0. 1.0 is natural.", "default": "1.0" }, "outputFormat": { "title": "Output format", "enum": [ "mp3", "wav" ], "type": "string", "description": "mp3 is the default for premium. The standard model always returns WAV.", "default": "mp3" }, "maxTexts": { "title": "Max texts per run", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop after this many texts. Protects against oversized lists. Default 200.", "default": 200 } } }, "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 } } } } } } } } } }