You're looking at a specific version of this model. Jump to the model overview.

minimax /voice-cloning:aa25ee12

Playground API

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
voice_file
string
Voice file to clone. Must be MP3, M4A, or WAV format, 10s to 5min duration, and less than 20MB.
need_noise_reduction
boolean
False
Enable noise reduction. Use this if the voice file has background noise.
model
None
speech-02-turbo
The text-to-speech model to train
accuracy
number
0.7

Max: 1

Text validation accuracy threshold (0-1)
need_volume_normalization
boolean
False
Enable volume normalization

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema 
{'properties': {'model': {'title': 'Model', 'type': 'string'},
                'preview': {'format': 'uri',
                            'title': 'Preview',
                            'type': 'string'},
                'voice_id': {'title': 'Voice Id', 'type': 'string'}},
 'required': ['voice_id', 'preview', 'model'],
 'title': 'VoiceCloningOutputs',
 'type': 'object'}