lucataco/singing_voice_conversion

Amphion Singing Voice Conversion: DiffWaveNetSVC

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`source_audio`*	string(uri)	Input source audio file	`—`	—
`diffusion_inference_steps`	integer	Diffusion inference steps	`1000`	min: 0, max: 1000
`key_shift_mode`	integer	Key shift values	`0`	min: -6, max: 6
`pitch_shift_control`	string	Pitch shift control	`"Auto Shift"`	Auto ShiftKey Shift
`target_singer`	string	Target singer to convert audio to	`"Taylor Swift"`	AdeleBeyonceBruno MarsJohn MayerMichael JacksonTaylor SwiftJacky Cheung 张学友Jian Li 李健Feng Wang 汪峰Faye Wong 王菲Yijie Shi 石倚洁Tsai Chin 蔡琴Ying Na 那英Eason Chan 陈奕迅David Tao 陶喆

source_audiorequiredstring

Input source audio file

diffusion_inference_stepsinteger

Diffusion inference steps

Default: 1000min: 0, max: 1000

key_shift_modeinteger

Key shift values

Default: 0min: -6, max: 6

pitch_shift_controlstring

Pitch shift control

Default: "Auto Shift"

Auto ShiftKey Shift

target_singerstring

Target singer to convert audio to

Default: "Taylor Swift"

AdeleBeyonceBruno MarsJohn MayerMichael JacksonTaylor SwiftJacky Cheung 张学友Jian Li 李健Feng Wang 汪峰Faye Wong 王菲Yijie Shi 石倚洁Tsai Chin 蔡琴Ying Na 那英Eason Chan 陈奕迅David Tao 陶喆

Version: f29872ee3557Updated: 7/25/20261.1K runs