minimax/voice-cloning

Clone voices to use with Minimax's speech-02-hd and speech-02-turbo

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`voice_file`*	string(uri)	Voice file to clone. Must be MP3, M4A, or WAV format, 10s to 5min duration, and less than 20MB.	`—`	—
`accuracy`	number	Text validation accuracy threshold (0-1)	`0.7`	min: 0, max: 1
`model`	string	The text-to-speech model to train	`"speech-02-turbo"`	speech-2.6-turbospeech-2.6-hdspeech-02-turbospeech-02-hd
`need_noise_reduction`	boolean	Enable noise reduction. Use this if the voice file has background noise.	`false`	—
`need_volume_normalization`	boolean	Enable volume normalization	`false`	—

voice_filerequiredstring

Voice file to clone. Must be MP3, M4A, or WAV format, 10s to 5min duration, and less than 20MB.

accuracynumber

Text validation accuracy threshold (0-1)

Default: 0.7min: 0, max: 1

modelstring

The text-to-speech model to train

Default: "speech-02-turbo"

speech-2.6-turbospeech-2.6-hdspeech-02-turbospeech-02-hd

need_noise_reductionboolean

Enable noise reduction. Use this if the voice file has background noise.

Default: false

need_volume_normalizationboolean

Enable volume normalization

Default: false

Version: fff8a670880fUpdated: 7/25/202644.7K runs