← Back to all generators

x-lance/f5-tts

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

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

gen_text required string

Text to Generate

ref_audio required string

Reference audio for voice cloning

custom_split_words string

Custom split words, comma separated

Default: ""
ref_text string

Reference Text

remove_silence boolean

Automatically remove silences?

Default: true
speed number

Speed of the generated audio

Default: 1 min: 0.1, max: 3
Version: 87faf6dd7a69 Updated: 2/26/2026 40.5K runs