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": "Invalid request format",
"type": "invalid_request_error"
}
}{
"error": {
"message": "Invalid API key",
"type": "authentication_error"
}
}{
"error": {
"message": "Insufficient account balance",
"type": "insufficient_quota"
}
}{
"error": {
"message": "Parameter validation failed",
"type": "validation_error"
}
}{
"error": {
"message": "Rate limit exceeded",
"type": "rate_limit_error"
}
}{
"error": {
"message": "Internal server error",
"type": "server_error"
}
}{
"error": {
"message": "Service temporarily unavailable, please try again later",
"type": "service_unavailable"
}
}Speech Recognition
Scribe V2 Speech Recognition
- Scribe V2 audio file recognition model
- Supports language specification, speaker diarization, audio event tagging, and keyterms biasing
- Asynchronous processing mode, use the returned task ID to query status
- Recognition results are returned in the
resultsfield of the task detail
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": "Invalid request format",
"type": "invalid_request_error"
}
}{
"error": {
"message": "Invalid API key",
"type": "authentication_error"
}
}{
"error": {
"message": "Insufficient account balance",
"type": "insufficient_quota"
}
}{
"error": {
"message": "Parameter validation failed",
"type": "validation_error"
}
}{
"error": {
"message": "Rate limit exceeded",
"type": "rate_limit_error"
}
}{
"error": {
"message": "Internal server error",
"type": "server_error"
}
}{
"error": {
"message": "Service temporarily unavailable, please try again later",
"type": "service_unavailable"
}
}Authorizations
All APIs require Bearer Token authentication
Add to request header:
Authorization: Bearer YOUR_API_KEY
Body
application/json
scribe-v2: Speech recognition model supporting diarize, audio event tagging, and keyterms
Example:
"scribe-v2"
Audio file URL to transcribe
Notes:
- Must be an HTTP/HTTPS accessible URL
- The audio file must be directly accessible and readable by the system
Example:
"https://samplelib.com/lib/preview/mp3/sample-3s.mp3"
Audio language code
Notes:
- Supports ISO-639-1 or ISO-639-3 codes
- Examples:
zh/zho/en/eng - Auto-detected if not provided
Example:
"zh"
Whether to tag audio events such as laughter and applause. Enabled by default.
Example:
true
Whether to perform speaker diarization. Enabled by default.
Example:
true
Bias terms / phrase list
Notes:
- Up to 100 entries
- Each entry up to 50 characters
- Used to boost recognition of specific terms or proper nouns
Do not pass this parameter unless necessary.
Maximum array length:
100Maximum string length:
50Example:
[
"project kickoff",
"quarterly results",
"speech to text"
]
Response
Task created successfully
Task creation timestamp
Example:
1757165031
Task ID
Example:
"task-unified-1757165031-uyujaw3d"
Actual model name used
Specific task type
Available options:
audio.generation.task Task progress percentage (0-100)
Required range:
0 <= x <= 100Example:
0
Task status
Available options:
pending, processing, completed, failed Example:
"pending"
Asynchronous task info
Show child attributes
Show child attributes
Task output type
Available options:
audio Example:
"audio"