Text To Speech

Text to speech using the chenxwh/openvoice AI Model.

Query

model

string

default: "chenxwh/openvoice"required

The voice model to be used;

Body

audio

file

required

Input reference audio

text

string

required

Input text

language

string

default: "EN_NEWEST"

The language of the audio to be generated

cleanup_voice

float

default: "1"

Set speed scale of the output audio