# VITS Architecture

Guarani text-to-speech model based on VITS architecture, built using the MMS-TTS framework

An advanced Arabic text-to-speech system based on the VITS architecture, capable of generating natural and realistic speech while understanding colloquial text

A lightweight text-to-speech model based on Facebook MMS-TTS Spanish version, specifically fine-tuned for Chilean Spanish accent

An Arabic speech synthesis model developed by Meta, based on the VITS architecture, supporting high-quality text-to-speech functionality.

A Mongolian text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

Turkish text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

A Turkmen text-to-speech model developed by Meta, part of the Massively Multilingual Speech project, supporting speech synthesis for Turkmen written in Latin script.

Luganda text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

A Haryanvi text-to-speech model developed by Meta, part of the Massively Multilingual Speech (MMS) project, utilizing the VITS end-to-end speech synthesis architecture.

Facebook MMS project's Polish text-to-speech model, based on VITS architecture, supports high-quality Polish speech synthesis

Bengali text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Bemba (bem) text-to-speech model developed by Meta, part of the Massively Multilingual Speech project

Spanish text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

A Somali text-to-speech model developed by Meta as part of the MMS project, supporting the conversion of Somali text into natural speech.

A Nigerian Pidgin text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

A Malay text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

A Gujarati text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

Kekchi text-to-speech model developed by Meta, part of the Massively Multilingual Speech project

Odia text-to-speech model from Facebook's MMS project, achieving high-quality speech synthesis based on the VITS architecture

Arabela language text-to-speech model developed by Meta, based on VITS architecture, supporting high-quality speech synthesis

Kannada text-to-speech model developed by Meta, based on VITS architecture, supporting high-quality speech synthesis

Latin text-to-speech model developed by Meta, based on VITS architecture, supporting high-quality speech synthesis

Romanian text-to-speech model developed by Meta, utilizing VITS architecture for high-quality speech synthesis

A French text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

A Javanese text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Persian text-to-speech model developed by Meta AI, based on the VITS architecture, supporting high-quality speech synthesis

Icelandic text-to-speech model developed by Meta, based on VITS architecture, supporting high-quality speech synthesis

An Ese Ehue text-to-speech model developed by Meta as part of the Massively Multilingual Speech project, supporting high-quality speech synthesis.

Temne text-to-speech model developed by Meta, part of the Massively Multilingual Speech (MMS) project

A Dutch text-to-speech model developed by Meta, part of the Massively Multilingual Speech project, utilizing the VITS end-to-end speech synthesis architecture.

Bulgarian text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

Facebook's Massively Multilingual Speech project's Tamil text-to-speech model, implementing high-quality speech synthesis based on the VITS architecture

A Maldivian text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

Korean text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis

Hungarian text-to-speech model developed by Facebook, based on the VITS architecture, supporting high-quality speech synthesis

Urdu (Latin script transcription) text-to-speech model developed by Meta, part of the MMS multilingual speech project

German standard text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality German speech synthesis

Hindi text-to-speech model developed by Facebook, based on VITS architecture, supporting high-quality speech synthesis

A Bororo text-to-speech model developed by Meta as part of the Massively Multilingual Speech (MMS) project, utilizing the VITS architecture for high-quality speech synthesis

Marathi text-to-speech model developed by Meta, supporting high-quality speech synthesis