curl --request POST \
--url https://api.aihubmax.com/v1/audios/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "scribe-v2",
"audio_url": "https://samplelib.com/lib/preview/mp3/sample-3s.mp3"
}
'
{
"created": 1757165031,
"id": "task-unified-1757165031-uyujaw3d",
"model": "<string>",
"object": "audio.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 45
},
"type": "audio"
}{
"error": {
"message": "请求格式错误",
"type": "invalid_request_error"
}
}{
"error": {
"message": "API密钥无效",
"type": "authentication_error"
}
}{
"error": {
"message": "账户余额不足",
"type": "insufficient_quota"
}
}{
"error": {
"message": "参数校验失败",
"type": "validation_error"
}
}{
"error": {
"message": "请求频率超限",
"type": "rate_limit_error"
}
}{
"error": {
"message": "服务器内部错误",
"type": "server_error"
}
}{
"error": {
"message": "服务暂不可用,请稍后重试",
"type": "service_unavailable"
}
}语音识别
Scribe V2 语音识别
- Scribe V2 录音文件识别模型
- 支持语言指定、说话人分离、音频事件标注与 keyterms 偏置词增强
- 异步处理模式,使用返回的任务ID 进行查询
- 识别结果会在任务详情的
results字段中返回
POST
/
v1
/
audios
/
generations
curl --request POST \
--url https://api.aihubmax.com/v1/audios/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "scribe-v2",
"audio_url": "https://samplelib.com/lib/preview/mp3/sample-3s.mp3"
}
'
{
"created": 1757165031,
"id": "task-unified-1757165031-uyujaw3d",
"model": "<string>",
"object": "audio.generation.task",
"progress": 0,
"status": "pending",
"task_info": {
"can_cancel": true,
"estimated_time": 45
},
"type": "audio"
}{
"error": {
"message": "请求格式错误",
"type": "invalid_request_error"
}
}{
"error": {
"message": "API密钥无效",
"type": "authentication_error"
}
}{
"error": {
"message": "账户余额不足",
"type": "insufficient_quota"
}
}{
"error": {
"message": "参数校验失败",
"type": "validation_error"
}
}{
"error": {
"message": "请求频率超限",
"type": "rate_limit_error"
}
}{
"error": {
"message": "服务器内部错误",
"type": "server_error"
}
}{
"error": {
"message": "服务暂不可用,请稍后重试",
"type": "service_unavailable"
}
}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
请求体
application/json
scribe-v2:支持 diarize、音频事件标注与 keyterms 的语音识别模型
示例:
"scribe-v2"
待识别音频文件 URL
说明:
- 需为 HTTP/HTTPS 可访问地址
- 音频文件需可被系统直接访问和读取
示例:
"https://samplelib.com/lib/preview/mp3/sample-3s.mp3"
音频语言代码
说明:
- 支持 ISO-639-1 或 ISO-639-3 代码
- 例如:
zh/zho/en/eng - 不传时由模型自动检测
示例:
"zh"
是否标注笑声、掌声等音频事件。默认开启。
示例:
true
是否进行说话人分离。默认开启。
示例:
true
偏置词 / 短语列表
说明:
- 最多 100 个条目
- 每个条目最多 50 个字符
- 用于提升特定术语或专有名词的识别倾向
非必须不要传这个参数。
Maximum array length:
100Maximum string length:
50示例:
[ "project kickoff", "quarterly results", "speech to text" ]
响应
任务创建成功
任务创建时间戳
示例:
1757165031
任务ID
示例:
"task-unified-1757165031-uyujaw3d"
实际使用的模型名称
任务的具体类型
可用选项:
audio.generation.task 任务进度百分比 (0-100)
必填范围:
0 <= x <= 100示例:
0
任务状态
可用选项:
pending, processing, completed, failed 示例:
"pending"
异步任务信息
Show child attributes
Show child attributes
任务的输出类型
可用选项:
audio 示例:
"audio"