{ "openapi": "3.0.1", "info": { "title": "AI Voice Cloning Text to Speech - English", "description": "Clone a voice from one short English recording and make it read any script with natural expression, including laughs and sighs. Built-in default voice, long text support, MP3/WAV/Opus output. No rental fee - you pay Apify compute only.", "version": "0.3", "x-build-id": "r2kXaJxVlDkXbWLPF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/andrew_babo~chatterbox-tts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-andrew_babo-chatterbox-tts", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/andrew_babo~chatterbox-tts/runs": { "post": { "operationId": "runs-sync-andrew_babo-chatterbox-tts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/andrew_babo~chatterbox-tts/run-sync": { "post": { "operationId": "run-sync-andrew_babo-chatterbox-tts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "text": { "title": "Text", "minLength": 1, "maxLength": 20000, "type": "string", "description": "Required English text to synthesize. Chatterbox automatically splits long text. Paralinguistic tags such as [laugh], [cough], and [chuckle] are experimental. Maximum 20,000 characters." }, "ref_audio_url": { "title": "Reference audio URL (voice cloning)", "type": "string", "description": "Public URL to 5-15 seconds of clean speech to clone. Leave empty to use the bundled default voice." }, "dtype": { "title": "Model precision", "enum": [ "fp32", "q4", "q8", "fp16", "q4f16" ], "type": "string", "description": "ONNX graph precision. fp32 is the tested default for Apify CPU.", "default": "fp32" }, "repetition_penalty": { "title": "Repetition penalty", "type": "string", "description": "Higher values reduce looping and stuttering artifacts in long passages.", "default": "1.2" }, "max_new_tokens": { "title": "Max speech tokens per chunk", "minimum": 64, "maximum": 2048, "type": "integer", "description": "Optional safety cap. Leave empty to estimate a safe budget from chunk length." }, "speed": { "title": "Speed", "type": "string", "description": "Playback rate multiplier applied after synthesis. 1.0 is natural.", "default": "1.0" }, "crossfade_ms": { "title": "Boundary fade (ms)", "minimum": 0, "maximum": 80, "type": "integer", "description": "Short fade at sentence boundaries to avoid clicks without removing the natural pause.", "default": 15 }, "trim_silence": { "title": "Trim chunk silence", "type": "boolean", "description": "Keep sentence pauses natural while removing excessive dead air at chunk edges.", "default": true }, "format": { "title": "Output format", "enum": [ "wav", "mp3", "opus" ], "type": "string", "description": "Container/codec of the returned audio file.", "default": "wav" }, "stream": { "title": "Stream audio", "type": "boolean", "description": "Reserved for a future streaming endpoint; keep false for the current stable audio response.", "default": false }, "chunk_chars": { "title": "Chunk size (characters)", "minimum": 80, "maximum": 400, "type": "integer", "description": "Short chunks reduce decoder drift and allow earlier streaming.", "default": 150 }, "chunk_parallel": { "title": "Parallel chunks", "minimum": 0, "maximum": 8, "type": "integer", "description": "0 uses the tuned default of 2 concurrent chunks; use 1 for lowest RAM.", "default": 0 } } }, "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 } } } } } } } } } }