Gemini Native

POST

https://api.aicombo.com/v1beta/models/{model_name}:{action}

Gemini audio generation endpoint. Supports models such as gemini-2.5-flash-preview-tts.
Returns audio data via inlineData.

For example:
/v1beta/models/gemini-3.1-flash-tts-preview:generateContent
/v1beta/models/gemini-3.1-flash-tts-preview:streamGenerateContent?alt=sse

请求参数

Path 参数

Query 参数

Header 参数

Body 参数application/json必填

示例

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Say in a cheerful tone: Hello, this is a speech synthesis test!"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "AUDIO"
    ],
    "speechConfig": {
      "voiceConfig": {
        "prebuiltVoiceConfig": {
          "voiceName": "Kore"
        }
      }
    }
  }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://api.aicombo.com/v1beta/models/gemini-3.1-flash-tts-preview:generateContent?alt=sse' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Say in a cheerful tone: Hello, this is a speech synthesis test!"
        }
      ]
    }
  ],
  "generationConfig": {
    "responseModalities": [
      "AUDIO"
    ],
    "speechConfig": {
      "voiceConfig": {
        "prebuiltVoiceConfig": {
          "voiceName": "Kore"
        }
      }
    }
  }
}'

返回响应

🟢200Success

application/json

Bodyapplication/json

示例

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "inlineData": {
              "mimeType": "audio/l16; rate=24000; channels=1",
              "data": ""
            }
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 23,
    "candidatesTokenCount": 132,
    "totalTokenCount": 155,
    "trafficType": "ON_DEMAND",
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 23
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "AUDIO",
        "tokenCount": 132
      }
    ]
  },
  "modelVersion": "gemini-3.1-flash-tts-preview",
  "createTime": "2026-06-23T07:30:10.333602Z",
  "responseId": "AjY6aqKuFMvO28sPu9-h2AY"
}

Text to Speech

ChatCompletions Format