curl --request POST \
--url https://api.aihubmax.com/v1beta/models/{model}:generateContent \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"contents": [
{
"role": "user",
"parts": [
{
"text": "创建一首 30 秒的欢快民谣，使用吉他和口琴。"
}
]
}
],
"generationConfig": {
"responseModalities": [
"AUDIO",
"TEXT"
]
}
}
'{
"candidates": [
{
"content": {
"parts": [
{
"text": "这是一首欢快的民谣，使用了吉他和口琴。",
"inlineData": {
"mimeType": "audio/mpeg",
"data": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4..."
}
}
],
"role": "model"
},
"finishReason": "STOP",
"safetyRatings": [
{
"category": "<string>",
"probability": "<string>"
}
]
}
],
"usageMetadata": {
"promptTokenCount": 15,
"candidatesTokenCount": 200,
"totalTokenCount": 215
}
}{
"error": {
"message": "请求参数无效",
"type": "http_error",
"code": 400,
"status": "INVALID_ARGUMENT"
}
}{
"error": {
"message": "API Key 无效",
"type": "authentication_error",
"code": 401,
"status": "UNAUTHENTICATED"
}
}{
"error": {
"message": "请求参数无效",
"type": "http_error",
"code": 400,
"status": "INVALID_ARGUMENT"
}
}{
"error": {
"message": "访问被拒绝",
"type": "permission_error",
"code": 403,
"status": "PERMISSION_DENIED"
}
}{
"error": {
"message": "请求频率超限",
"type": "rate_limit_error",
"code": 429,
"status": "RESOURCE_EXHAUSTED"
}
}{
"error": {
"message": "内部服务器错误",
"type": "server_error",
"code": 500,
"status": "UNKNOWN"
}
}Gemini 格式
Gemini 格式 - 音乐生成
- 使用 Gemini 原生格式的 generateContent 接口，通过 Lyria 3 模型生成音乐
- 通过
generationConfig.responseModalities包含AUDIO启用音频输出；若同时包含TEXT，响应会额外返回文本描述（歌词/结构） - 支持文本 prompt 和图片输入（最多 10 张），图片用于激发视觉灵感驱动的音乐创作
- 时长、结构（主歌/副歌/桥段）、风格等主要通过文本 prompt 控制
lyria-3-clip-preview：固定生成 30 秒短片段，默认返回 MP3（audio/mpeg）lyria-3-pro-preview：生成完整歌曲；可通过responseMimeType请求audio/mpeg或audio/wav，但实际输出格式请以响应中的inlineData.mimeType为准- 如需 SSE 流式输出，请使用
/v1beta/models/{model}:streamGenerateContent?alt=sse - 音乐生成为单轮过程，不支持多轮迭代编辑
POST
/
v1beta
/
models
/
{model}
:generateContent
curl --request POST \
--url https://api.aihubmax.com/v1beta/models/{model}:generateContent \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"contents": [
{
"role": "user",
"parts": [
{
"text": "创建一首 30 秒的欢快民谣，使用吉他和口琴。"
}
]
}
],
"generationConfig": {
"responseModalities": [
"AUDIO",
"TEXT"
]
}
}
'{
"candidates": [
{
"content": {
"parts": [
{
"text": "这是一首欢快的民谣，使用了吉他和口琴。",
"inlineData": {
"mimeType": "audio/mpeg",
"data": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4..."
}
}
],
"role": "model"
},
"finishReason": "STOP",
"safetyRatings": [
{
"category": "<string>",
"probability": "<string>"
}
]
}
],
"usageMetadata": {
"promptTokenCount": 15,
"candidatesTokenCount": 200,
"totalTokenCount": 215
}
}{
"error": {
"message": "请求参数无效",
"type": "http_error",
"code": 400,
"status": "INVALID_ARGUMENT"
}
}{
"error": {
"message": "API Key 无效",
"type": "authentication_error",
"code": 401,
"status": "UNAUTHENTICATED"
}
}{
"error": {
"message": "请求参数无效",
"type": "http_error",
"code": 400,
"status": "INVALID_ARGUMENT"
}
}{
"error": {
"message": "访问被拒绝",
"type": "permission_error",
"code": 403,
"status": "PERMISSION_DENIED"
}
}{
"error": {
"message": "请求频率超限",
"type": "rate_limit_error",
"code": 429,
"status": "RESOURCE_EXHAUSTED"
}
}{
"error": {
"message": "内部服务器错误",
"type": "server_error",
"code": 500,
"status": "UNKNOWN"
}
}授权
所有接口均需要使用Bearer Token进行认证
使用时在请求头中添加：
Authorization: Bearer YOUR_API_KEY
路径参数
模型名称。lyria-3-clip-preview 生成 30 秒短片段（默认 MP3 / audio/mpeg）。lyria-3-pro-preview 生成完整歌曲；可请求 audio/mpeg 或 audio/wav，实际输出格式以返回的 inlineData.mimeType 为准
可用选项:
lyria-3-clip-preview, lyria-3-pro-preview 示例:
"lyria-3-clip-preview"
请求体
application/json