x-lance/f5-tts

F5-TTS, the new state-of-the-art in open source voice cloning

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`gen_text`*	string	Text to Generate	`—`	—
`ref_audio`*	string(uri)	Reference audio for voice cloning	`—`	—
`custom_split_words`	string	Custom split words, comma separated	`""`	—
`ref_text`	string	Reference Text	`—`	—
`remove_silence`	boolean	Automatically remove silences?	`true`	—
`speed`	number	Speed of the generated audio	`1`	min: 0.1, max: 3

gen_textrequiredstring

Text to Generate

ref_audiorequiredstring

Reference audio for voice cloning

custom_split_wordsstring

Custom split words, comma separated

Default: ""

ref_textstring

Reference Text

remove_silenceboolean

Automatically remove silences?

Default: true

speednumber

Speed of the generated audio

Default: 1min: 0.1, max: 3

Version: 87faf6dd7a69Updated: 7/25/202640.5K runs