{
  "openapi": "3.1.0",
  "info": {
    "title": "kokoro — Chutes API",
    "description": "Text-to-speech with hexgrad/Kokoro-82M",
    "version": "37e5edcd-1eab-52d9-9bbb-f36a90d39a6d",
    "contact": {
      "name": "Chutes",
      "url": "https://chutes.ai"
    },
    "x-chutes": {
      "chuteId": "4be47dee-7bee-53a4-a208-32a66f47a0b0",
      "slug": "chutes-kokoro",
      "modelName": "kokoro",
      "standardTemplate": null,
      "openaiCompatible": false,
      "confidentialCompute": true,
      "modelPage": "https://chutes.ai/app/chute/chutes-kokoro",
      "llmsTxt": "https://chutes.ai/app/chute/chutes-kokoro/llms.txt",
      "pricing": {
        "usdPerHour": 1.8
      }
    }
  },
  "servers": [
    {
      "url": "https://chutes-kokoro.chutes.ai"
    }
  ],
  "security": [
    {
      "bearerAuth": []
    }
  ],
  "components": {
    "securitySchemes": {
      "bearerAuth": {
        "type": "http",
        "scheme": "bearer",
        "description": "Chutes API key. Send as `Authorization: Bearer $CHUTES_API_KEY`."
      }
    }
  },
  "paths": {
    "/speak": {
      "post": {
        "operationId": "speak",
        "summary": "POST /speak",
        "responses": {
          "200": {
            "description": "Binary media payload.",
            "content": {
              "audio/wav": {
                "schema": {
                  "type": "string",
                  "format": "binary"
                }
              }
            }
          }
        },
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "properties": {
                  "text": {
                    "type": "string"
                  },
                  "speed": {
                    "type": "number",
                    "description": "Voice output speed.",
                    "default": 1,
                    "minimum": 0.1,
                    "maximum": 3
                  },
                  "voice": {
                    "type": "string",
                    "description": "Voice selection for text-to-speech",
                    "enum": [
                      "af_heart",
                      "af_alloy",
                      "af_aoede",
                      "af_bella",
                      "af_jessica",
                      "af_kore",
                      "af_nicole",
                      "af_nova",
                      "af_river",
                      "af_sarah",
                      "af_sky",
                      "am_adam",
                      "am_echo",
                      "am_eric",
                      "am_fenrir",
                      "am_liam",
                      "am_michael",
                      "am_onyx",
                      "am_puck",
                      "am_santa",
                      "bf_alice",
                      "bf_emma",
                      "bf_isabella",
                      "bf_lily",
                      "bm_daniel",
                      "bm_fable",
                      "bm_george",
                      "bm_lewis",
                      "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"
                    ],
                    "default": "af_heart"
                  }
                },
                "required": [
                  "text"
                ]
              },
              "example": {
                "text": "Your text here",
                "speed": 1,
                "voice": "af_heart"
              }
            }
          }
        }
      }
    }
  }
}