Native Gemini Format TTS

POST

/v1beta/models/{model}:generateContent

Native Gemini (Speech)

Call AboAI API using the native Google Gemini format

Introduction

The Gemini Native API adopts the request and response format of Google Gemini. It is suitable for official Google clients (such as the google-generativeai SDK) or scenarios that require direct utilization of Gemini data structures. This interface complies with the Gemini API specifications and fully supports features like Thinking mode, multimodal input, tool calling, Google Search (Grounding), and image generation.

API Endpoints

Feature	Method	Path
Content Generation (Non-streaming)	POST	`/v1beta/models/{model}:generateContent`

Authentication

Either of the following methods is supported:

Header Parameter	Type	Description
`Authorization`	string	Bearer Token: `Bearer sk-xxxxxxxxxx` (Recommended, consistent with other AboAI endpoints)
`x-goog-api-key`	string	Google-style API Key: `x-goog-api-key: sk-xxxxxxxxxx`

Alternatively, parameters can be passed in the URL: ?key=sk-xxxxxxxxxx.

请求参数

Path 参数

Query 参数

Header 参数

Body 参数application/json

示例

{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Read aloud: Hello World"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "AUDIO"
        ],
        "speechConfig": {
            "voiceConfig": {
                "prebuiltVoiceConfig": {
                    "voiceName": "Kore"
                }
            },
            "languageCode": "cmn-CN"
        },
        "maxOutputTokens": 4096
    }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://api.peakkai.ai/v1beta/models/gemini-2.5-pro-tts:generateContent?key=undefined' \
--header 'x-goog-api-key;' \
--header 'Authorization;' \
--header 'Content-Type: application/json' \
--data '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Read aloud: Hello World"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "AUDIO"
        ],
        "speechConfig": {
            "voiceConfig": {
                "prebuiltVoiceConfig": {
                    "voiceName": "Kore"
                }
            },
            "languageCode": "cmn-CN"
        },
        "maxOutputTokens": 4096
    }
}'

返回响应

🟢200

application/json

Bodyapplication/json

示例

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "inlineData": {
              "data": "",
              "mimeType": "audio/L16;codec=pcm;rate=24000"
            }
          }
        ],
        "role": "model"
      },
      "index": 0,
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": integer,
    "candidatesTokenCount": integer,
    "totalTokenCount": integer,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": integer
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "AUDIO",
        "tokenCount": integer
      }
    ]
  },
  "modelVersion": "gemini-2.5-pro-tts",
  "responseId": "MnjYaaqvHvnasbwP2J33iAQ"
}

修改于 2026-11-02 09:46:28

Native OpenAI Format TTS

Native OpenAI Format Image Editing (JSON)

Native Gemini Format TTS

Native Gemini (Speech)#

Introduction#

API Endpoints#