xtts-v2

Multilingual Text-To-Speech voice cloning model

Hold: 0

Required: 25,000 $wRAI

47.4k runs

Input

text

Text to synthesize

language

Language

speaker

Click to select a file to input

Original speaker audio

Hold at least 25,000 wRAI to use this model

Multi AI platform is completely free, but most models are only accessible to wRAI token holders. If you have any questions, feel free to ask in our Telegram chat

Output

Download

Input

language

speaker

text

Wrapped RubyAI is a platform for open-source products built using artificial intelligence technology. Our service provides a unique opportunity to use all the most in-demand neural networks in one place at a fair price. Any developer will be able to monetize their AI model, which will be deployed inside our server and run on Nvidia T4 GPU.

Output

Download

Readme

xtts-v2 the Open, Foundation Speech Model by Coqui 🐸

Language Settings: English: en 🇺🇸 French: fr 🇫🇷 German: de 🇩🇪 Spanish: es 🇪🇸 Italian: it 🇮🇹 Portuguese: pt 🇵🇹 Czech: cs 🇨🇿 Polish: pl 🇵🇱 Russian: ru 🇷🇺 Dutch: nl 🇳🇱 Turksih: tr 🇹🇷 Arabic: ar 🇦🇪 Mandarin Chinese: zh-cn 🇨🇳

Сортировать по: