curl --request POST \
--url https://api.aihubmax.com/v1/audios/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "paraformer-v2",
"file_urls": [
"https://example.com/audio/meeting.wav"
]
}
'{
"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"
}
}Paraformer V2 Speech Recognition
- Paraformer V2 audio file recognition model, supports Chinese (including dialects), English, Japanese, and other languages
- Supports speaker diarization, hot word customization, and disfluency filtering
- Asynchronous processing mode, use the returned task ID to query status
- Recognition results are returned in the
resultsfield of the task detail
curl --request POST \
--url https://api.aihubmax.com/v1/audios/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "paraformer-v2",
"file_urls": [
"https://example.com/audio/meeting.wav"
]
}
'{
"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
paraformer-v2: Supports Chinese, English, Japanese, and other languages
paraformer-8k-v2: 8kHz sample rate, Chinese only
"paraformer-v2"
"paraformer-8k-v2"
Audio file URL list
Notes:
- Supports publicly accessible URLs via HTTP/HTTPS
- Up to 100 URLs per request
- Supported formats: aac, amr, avi, flac, flv, m4a, mkv, mov, mp3, mp4, mpeg, ogg, opus, wav, webm, wma, wmv
- Single file must not exceed 2GB and 12 hours in duration
1 - 100 elements["https://example.com/audio/meeting.wav"]
Language hints for recognition
Notes:
- Only supported by
paraformer-v2, not applicable toparaformer-8k-v2 - Supported language codes:
zh(Chinese),en(English),ja(Japanese),yue(Cantonese),ko(Korean),de(German),fr(French),ru(Russian)
["zh", "en"]
Audio track index
Notes:
- Index starts from 0,
[0]means the first track - Default is
[0](only process the first track) - Each specified track is billed independently
Do not pass this parameter unless necessary.
[0]
Recognition configuration
Notes:
- Includes disfluency filtering, timestamp alignment, hot words, and sensitive word filter settings
- If not provided, default configuration is used
Do not pass this parameter unless necessary.
Show child attributes
Show child attributes
Speaker diarization configuration
Notes:
- Includes diarization toggle and speaker count hint
- If not provided, speaker diarization is not enabled
Do not pass this parameter unless necessary.
Show child attributes
Show child attributes
Response
Task created successfully
Task creation timestamp
1757165031
Task ID
"task-unified-1757165031-uyujaw3d"
Actual model name used
Specific task type
audio.generation.task Task progress percentage (0-100)
0 <= x <= 1000
Task status
pending, processing, completed, failed "pending"
Asynchronous task info
Show child attributes
Show child attributes
Task output type
audio "audio"