{ "openapi": "3.0.1", "info": { "title": "Kokoro Text to Speech - 54 voices, 9 languages, MP3 output", "description": "Turn text into natural speech with the Kokoro-82M model. 54 voices, 9 languages, MP3/WAV/Opus/FLAC.", "version": "0.1", "x-build-id": "6jpVUfZlrUTGWebeX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/superslowsloth~kokoro-text-to-speech/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-superslowsloth-kokoro-text-to-speech", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/superslowsloth~kokoro-text-to-speech/runs": { "post": { "operationId": "runs-sync-superslowsloth-kokoro-text-to-speech", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/superslowsloth~kokoro-text-to-speech/run-sync": { "post": { "operationId": "run-sync-superslowsloth-kokoro-text-to-speech", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "texts" ], "properties": { "texts": { "title": "Texts to speak", "type": "array", "description": "One entry per audio file. Long entries are split at sentence boundaries and joined back into a single file, so a whole article can go in one line. Up to 500,000 characters per run.", "items": { "type": "string" } }, "voice": { "title": "Voice", "enum": [ "af_heart", "af_bella", "af_nicole", "af_sarah", "af_sky", "af_alloy", "af_aoede", "af_jessica", "af_kore", "af_nova", "af_river", "am_adam", "am_michael", "am_echo", "am_eric", "am_fenrir", "am_liam", "am_onyx", "am_puck", "am_santa", "bf_emma", "bf_isabella", "bf_alice", "bf_lily", "bm_george", "bm_lewis", "bm_daniel", "bm_fable", "ef_dora", "em_alex", "em_santa", "ff_siwis", "hf_alpha", "hf_beta", "hm_omega", "hm_psi", "if_sara", "im_nicola", "jf_alpha", "jf_gongitsune", "jf_nezumi", "jf_tebukuro", "jm_kumo", "pf_dora", "pm_alex", "pm_santa", "zf_xiaobei", "zf_xiaoni", "zf_xiaoxiao", "zf_xiaoyi", "zm_yunjian", "zm_yunxi", "zm_yunxia", "zm_yunyang" ], "type": "string", "description": "Voice pack to speak with. The first letter is the accent (a: American, b: British, e: Spanish, f: French, h: Hindi, i: Italian, j: Japanese, p: Portuguese, z: Mandarin), the second is the speaker's gender.", "default": "af_heart" }, "language": { "title": "Language", "enum": [ "en-us", "en-gb", "es", "fr-fr", "hi", "it", "ja", "pt-br", "cmn" ], "type": "string", "description": "Which pronunciation rules the text is read with. Match it to the voice: a Japanese voice reading English with American rules sounds wrong in a way no voice choice fixes.", "default": "en-us" }, "speed": { "title": "Speaking speed", "enum": [ "0.5", "0.75", "0.9", "1.0", "1.1", "1.25", "1.5", "2.0" ], "type": "string", "description": "Playback rate the model speaks at. 1.0 is the model's natural pace.", "default": "1.0" }, "audioFormat": { "title": "Audio format", "enum": [ "mp3", "wav", "opus", "flac", "aac" ], "type": "string", "description": "Container the audio is delivered in. MP3 plays everywhere; WAV is uncompressed and much larger; Opus is the smallest at the same quality.", "default": "mp3" }, "precision": { "title": "Model precision", "enum": [ "int8", "fp32" ], "type": "string", "description": "Full precision sounds slightly cleaner on sibilants. Quantised is markedly faster, which on a per-character price is what you are paying for.", "default": "int8" } } }, "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 } } } } } } } } } }