跳到正文
API 参考
API 参考

Gemini TTS Text-to-Speech

以异步 Task 提交Text to Speech请求。

查看 Markdown
01

概览

使用支持的模型提交Text to Speech请求。使用返回的 Task ID 查询状态，或提供 callback_url 接收下方列出的投递。

快速开始

  1. 创建 API Key，并将其设置为 RUNAPI_API_KEY。
  2. 选择一个支持的模型，并发送与该模型 Schema 匹配的 POST 请求。
  3. 保存返回的任务 ID，随后轮询到终态，或处理下方列出的回调。

端点

POST /api/v1/gemini_tts/text_to_speech
基础 URL
https://runapi.ai
API 版本
v1
身份验证
Authorization: Bearer YOUR_API_TOKEN
02

支持的模型

打开模型页可查看当前价格、限流和商业使用详情。

03

请求 Schema

JSON 请求体

字段和允许的取值取决于所选模型。提供 callback_url 后，它会收到下方列出的 Task 投递。

gemini-2.5-pro-tts15 个字段
callback_urlstring
可选

Webhook URL for async notifications.

dialogue_turnsarray
必填

Non-empty ordered dialogue turns whose speaker ids reference configured speakers.

项数限制: 1
dialogue_turns[].speaker_idstring
必填

Identifier matching a configured speakers[].speaker_id.

dialogue_turns[].textstring
必填

Spoken text, up to 10,000 characters.

边界: 10000
modelstring
必填

Model slug.

sample_contextstring
可选

Overall delivery context and tone.

scenestring
可选

Scene and recording environment.

speakersarray
必填

Non-empty speaker configurations with unique Speaker N identifiers.

项数限制: 1
speakers[].accentstring
可选

Speaker accent.

可选值: Neutral, American (Gen), American (Valley), American (South), British (RP), British (Brixton), Transatlantic, Australian
speakers[].audio_profilestring
可选

Optional voice character guidance.

speakers[].pacestring
可选

Speaker pace.

可选值: Natural, Rapid Fire, The Drift, Staccato
speakers[].speaker_idstring
必填

Unique identifier in Speaker N format.

speakers[].stylestring
可选

Speaker delivery style.

可选值: Vocal Smile, Newscaster, Whisper, Empathetic, Promo/Hype, Deadpan
speakers[].voice_namestring
必填

Preset voice name.

可选值: Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Puck, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi
temperaturenumber
可选

Sampling temperature.

默认值: 1 范围: 0 - 2
gemini-3.1-flash-tts15 个字段
callback_urlstring
可选

Webhook URL for async notifications.

dialogue_turnsarray
必填

Non-empty ordered dialogue turns whose speaker ids reference configured speakers.

项数限制: 1
dialogue_turns[].speaker_idstring
必填

Identifier matching a configured speakers[].speaker_id.

dialogue_turns[].textstring
必填

Spoken text, up to 10,000 characters.

边界: 10000
modelstring
必填

Model slug.

sample_contextstring
可选

Overall delivery context and tone.

scenestring
可选

Scene and recording environment.

speakersarray
必填

Non-empty speaker configurations with unique Speaker N identifiers.

项数限制: 1
speakers[].accentstring
可选

Speaker accent.

可选值: Neutral, American (Gen), American (Valley), American (South), British (RP), British (Brixton), Transatlantic, Australian
speakers[].audio_profilestring
可选

Optional voice character guidance.

speakers[].pacestring
可选

Speaker pace.

可选值: Natural, Rapid Fire, The Drift, Staccato
speakers[].speaker_idstring
必填

Unique identifier in Speaker N format.

speakers[].stylestring
可选

Speaker delivery style.

可选值: Vocal Smile, Newscaster, Whisper, Empathetic, Promo/Hype, Deadpan
speakers[].voice_namestring
必填

Preset voice name.

可选值: Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Puck, Pulcherrima, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi
temperaturenumber
可选

Sampling temperature.

默认值: 1 范围: 0 - 2
04

创建已接受

HTTP 202

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "billing": {
      "properties": {
        "refund": {
          "oneOf": [
            {
              "properties": {
                "refunded_at": {
                  "type": "string"
                }
              },
              "required": [
                "refunded_at"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "reservation": {
          "oneOf": [
            {
              "properties": {
                "amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "amount_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "settlement": {
          "oneOf": [
            {
              "properties": {
                "amount_micro_cents": {
                  "type": "integer"
                },
                "charged_amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "charged_amount_cents",
                "amount_micro_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        }
      },
      "required": [
        "reservation",
        "settlement",
        "refund"
      ],
      "type": "object",
      "unevaluatedProperties": false
    },
    "id": {
      "type": "string"
    },
    "status": {
      "enum": [
        "processing"
      ],
      "type": "string"
    },
    "task_replayed": {
      "type": "boolean"
    }
  },
  "required": [
    "id",
    "status",
    "billing"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "billing": {
    "refund": null,
    "reservation": null,
    "settlement": null
  },
  "id": "tsk_reference_demo",
  "status": "processing"
}
05

轮询处理中

HTTP 200

GET /api/v1/gemini_tts/text_to_speech/:id

响应 Schema
JSON 
{
  "properties": {
    "billing": {
      "properties": {
        "refund": {
          "oneOf": [
            {
              "properties": {
                "refunded_at": {
                  "type": "string"
                }
              },
              "required": [
                "refunded_at"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "reservation": {
          "oneOf": [
            {
              "properties": {
                "amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "amount_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "settlement": {
          "oneOf": [
            {
              "properties": {
                "amount_micro_cents": {
                  "type": "integer"
                },
                "charged_amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "charged_amount_cents",
                "amount_micro_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        }
      },
      "required": [
        "reservation",
        "settlement",
        "refund"
      ],
      "type": "object",
      "unevaluatedProperties": false
    },
    "id": {
      "type": "string"
    },
    "status": {
      "enum": [
        "processing"
      ],
      "type": "string"
    }
  },
  "required": [
    "id",
    "status",
    "billing"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "billing": {
    "refund": null,
    "reservation": null,
    "settlement": null
  },
  "id": "tsk_reference_demo",
  "status": "processing"
}
06

轮询已完成

HTTP 200

GET /api/v1/gemini_tts/text_to_speech/:id

响应 Schema
JSON 
{
  "properties": {
    "audios": {
      "items": {
        "properties": {
          "url": {
            "type": "string",
            "x-runapi-generated-media": true
          }
        },
        "required": [
          "url"
        ],
        "type": "object",
        "unevaluatedProperties": false
      },
      "type": "array"
    },
    "billing": {
      "properties": {
        "refund": {
          "oneOf": [
            {
              "properties": {
                "refunded_at": {
                  "type": "string"
                }
              },
              "required": [
                "refunded_at"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "reservation": {
          "oneOf": [
            {
              "properties": {
                "amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "amount_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "settlement": {
          "oneOf": [
            {
              "properties": {
                "amount_micro_cents": {
                  "type": "integer"
                },
                "charged_amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "charged_amount_cents",
                "amount_micro_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        }
      },
      "required": [
        "reservation",
        "settlement",
        "refund"
      ],
      "type": "object",
      "unevaluatedProperties": false
    },
    "id": {
      "type": "string"
    },
    "status": {
      "enum": [
        "completed"
      ],
      "type": "string"
    }
  },
  "required": [
    "id",
    "status",
    "audios",
    "billing"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "audios": [
    {
      "url": "https://file.runapi.ai/reference-audio.mp3"
    }
  ],
  "billing": {
    "refund": null,
    "reservation": null,
    "settlement": null
  },
  "id": "tsk_reference_demo",
  "status": "completed"
}
07

轮询失败

HTTP 200

GET /api/v1/gemini_tts/text_to_speech/:id

响应 Schema
JSON 
{
  "properties": {
    "billing": {
      "properties": {
        "refund": {
          "oneOf": [
            {
              "properties": {
                "refunded_at": {
                  "type": "string"
                }
              },
              "required": [
                "refunded_at"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "reservation": {
          "oneOf": [
            {
              "properties": {
                "amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "amount_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        },
        "settlement": {
          "oneOf": [
            {
              "properties": {
                "amount_micro_cents": {
                  "type": "integer"
                },
                "charged_amount_cents": {
                  "type": "integer"
                }
              },
              "required": [
                "charged_amount_cents",
                "amount_micro_cents"
              ],
              "type": "object",
              "unevaluatedProperties": false
            },
            {
              "enum": [
                null
              ]
            }
          ]
        }
      },
      "required": [
        "reservation",
        "settlement",
        "refund"
      ],
      "type": "object",
      "unevaluatedProperties": false
    },
    "error": {
      "type": "string"
    },
    "id": {
      "type": "string"
    },
    "status": {
      "enum": [
        "failed"
      ],
      "type": "string"
    }
  },
  "required": [
    "id",
    "status",
    "error",
    "billing"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "billing": {
    "refund": null,
    "reservation": null,
    "settlement": null
  },
  "error": "Task processing failed.",
  "id": "tsk_reference_demo",
  "status": "failed"
}
08

客户回调：已完成

HTTP 200

POST callback_url

响应 Schema
JSON 
{
  "properties": {
    "audios": {
      "items": {
        "properties": {
          "url": {
            "type": "string",
            "x-runapi-generated-media": true
          }
        },
        "required": [
          "url"
        ],
        "type": "object",
        "unevaluatedProperties": false
      },
      "type": "array"
    },
    "id": {
      "type": "string"
    },
    "status": {
      "enum": [
        "completed"
      ],
      "type": "string"
    }
  },
  "required": [
    "id",
    "status",
    "audios"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "audios": [
    {
      "url": "https://file.runapi.ai/reference-audio.mp3"
    }
  ],
  "id": "tsk_reference_demo",
  "status": "completed"
}
09

客户回调：失败

HTTP 200

POST callback_url

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "properties": {
            "code": {
              "type": "string"
            },
            "limit_cents": {
              "type": "integer"
            },
            "message": {
              "type": "string"
            },
            "reset_at": {
              "format": "date-time",
              "type": [
                "string",
                "null"
              ]
            },
            "used_cents": {
              "type": "integer"
            },
            "window": {
              "enum": [
                "1h",
                "1d",
                "7d",
                "daily",
                "weekly",
                "monthly",
                "lifetime"
              ],
              "type": "string"
            }
          },
          "required": [
            "code",
            "message"
          ],
          "type": "object",
          "unevaluatedProperties": false
        }
      ]
    },
    "id": {
      "type": "string"
    },
    "status": {
      "enum": [
        "failed"
      ],
      "type": "string"
    }
  },
  "required": [
    "id",
    "status",
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": {
    "code": "generation_failed",
    "message": "Task processing failed."
  },
  "id": "tsk_reference_demo",
  "status": "failed"
}
10

错误

HTTP 401

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "Authentication required"
}
11

错误

HTTP 401

GET /api/v1/gemini_tts/text_to_speech/:id

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "Authentication required"
}
12

错误

HTTP 400

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "oneOf": [
    {
      "properties": {
        "error": {
          "description": "Human-readable error message.",
          "type": "string"
        }
      },
      "required": [
        "error"
      ],
      "type": "object",
      "unevaluatedProperties": false
    },
    {
      "properties": {
        "error": {
          "description": "Human-readable validation summary.",
          "type": "string"
        },
        "errors": {
          "additionalProperties": {
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "description": "Validation messages keyed by public request field, with an array of human-readable strings for each field.",
          "type": "object"
        }
      },
      "required": [
        "error",
        "errors"
      ],
      "type": "object",
      "unevaluatedProperties": false
    }
  ]
}

响应示例

JSON 
{
  "error": "model must be one of: gemini-2.5-pro-tts, gemini-3.1-flash-tts"
}
13

错误

HTTP 402

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "Insufficient balance"
}
14

错误

HTTP 429

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "API key credit limit exceeded"
}
15

错误

HTTP 409

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "The request uses features that are not supported for the selected model"
}
16

错误

HTTP 429

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "Rate limit reached. Please retry later."
}
17

错误

HTTP 503

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "Service under maintenance, please try again later"
}
18

错误

HTTP 504

POST /api/v1/gemini_tts/text_to_speech

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "The request timed out"
}
19

错误

HTTP 404

GET /api/v1/gemini_tts/text_to_speech/:id

响应 Schema
JSON 
{
  "properties": {
    "error": {
      "description": "Human-readable error message.",
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "type": "object",
  "unevaluatedProperties": false
}

响应示例

JSON 
{
  "error": "Task with id 'tsk_reference_demo' not found"
}
20

生成的代码示例

直接使用 cURL，或安装所用语言的 SDK。每个示例都会提交本参考中经过验证的请求。

安装

Shell 
pip install runapi-gemini-tts
PYTHON 
import os
from runapi.gemini_tts import GeminiTtsClient

client = GeminiTtsClient(api_key=os.environ["RUNAPI_API_KEY"])
task = client.text_to_speech.create(
  model="gemini-2.5-pro-tts",
  temperature=0.8,
  scene="A quiet recording studio",
  sample_context="Natural conversational delivery",
  speakers=[{"speaker_id": "Speaker 1", "voice_name": "Fenrir", "audio_profile": "A calm host", "accent": "British (RP)", "style": "Newscaster", "pace": "Natural"}, {"speaker_id": "Speaker 2", "voice_name": "Puck", "accent": "American (Gen)", "style": "Empathetic", "pace": "Staccato"}],
  dialogue_turns=[{"speaker_id": "Speaker 1", "text": "Welcome to the show."}, {"speaker_id": "Speaker 2", "text": "Thanks for having me."}]
)