Gemini 格式

POST

/v1beta/models/{model}:generateContent

使用 Gemini 模型生成音频/语音。

通过 generationConfig.responseModalities 设置为 ["AUDIO"] 并配置 speechConfig 来生成语音输出。

支持的模型：

gemini-2.5-flash-preview-tts

gemini-2.0-flash-live-001

请求参数

Authorization

Bearer Token

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Path 参数

Body 参数application/json

示例

{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Say cheerfully: Have a wonderful day!"
                }
            ]
        }
    ],
    "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 --request POST 'https://api.llmhub.com.cn/v1beta/models/gemini-2.5-flash-preview-tts:generateContent' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Say cheerfully: Have a wonderful day!"
                }
            ]
        }
    ],
    "generationConfig": {
        "responseModalities": [
            "AUDIO"
        ],
        "speechConfig": {
            "voiceConfig": {
                "prebuiltVoiceConfig": {
                    "voiceName": "Kore"
                }
            }
        }
    }
}'

返回响应

🟢200

application/json

成功生成音频

Body

示例

{
    "candidates": [
        {
            "content": {
                "role": "model",
                "parts": [
                    {
                        "inlineData": {
                            "mimeType": "audio/wav",
                            "data": "UklGRiQAAABXQVZFZm10IBAAAAABAAEARKwAAIhYAQACABAAZGF0YQAAAAA="
                        }
                    }
                ]
            },
            "finishReason": "STOP"
        }
    ],
    "usageMetadata": {
        "promptTokenCount": 10,
        "candidatesTokenCount": 100,
        "totalTokenCount": 110
    }
}

修改于 2025-12-22 14:12:38

音频翻译

创建视频