lucataco/xtts-v2

Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`speaker`*	string(uri)	Original speaker audio (wav, mp3, m4a, ogg, or flv)	`—`	—
`cleanup_voice`	boolean	Whether to apply denoising to the speaker audio (microphone recordings)	`false`	—
`language`	string	Output language for the synthesised speech	`"en"`	enesfrdeitptpltrrunlcsarzhhukohi
`text`	string	Text to synthesize	`"Hi there, I'm your new voice clone. Try your best to upload quality audio"`	—

speakerrequiredstring

Original speaker audio (wav, mp3, m4a, ogg, or flv)

cleanup_voiceboolean

Whether to apply denoising to the speaker audio (microphone recordings)

Default: false

languagestring

Output language for the synthesised speech

Default: "en"

enesfrdeitptpltrrunlcsarzhhukohi

textstring

Text to synthesize

Default: "Hi there, I'm your new voice clone. Try your best to upload quality audio"

Version: 684bc3855b37Updated: 7/25/20265.0M runs