XTTS

Generate long vocal from text in several languages following voice freely, without account, without watermark and download it
XTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 3-second audio clip.
XTTS is built on previous research, like Tortoise, with additional architectural innovations and training to make cross-language voice cloning and multilingual speech generation possible.
This is the same model that powers our creator application Coqui Studio as well as the Coqui API. In production we apply modifications to make low-latency streaming possible.
Leave a star on the Github TTS, where our open-source inference and training code lives.

To avoid the queue, you can duplicate this space on CPU, GPU or ZERO space GPU:

Text Prompt

One or two sentences at a time is better

Language

Select an output language for the synthesised speech

More languages here

Gender

Gender of the voice

female male

Reference Audio (10 min. seems ideal)

Use Microphone for Reference

Notice: Microphone input may not work properly under traffic

Check to use Microphone as Reference

Generation number

How many audios to generate

1 9

Synthesised Audio #1

XTTS on your computer

You can install Pinokio locally and then install XTTS into it. It should be quite easy if you have an Nvidia GPU. You can also install XTTS on your computer using docker but it's more complicate.