# End-to-End Speech Generation

This is a Transformers-based Text-to-Speech (TTS) model capable of converting input text into natural speech output.

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

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.

Bengali 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 South Azerbaijani text-to-speech model developed by Meta, 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

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

A Tajik text-to-speech model developed by Meta, based on the 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.

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

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

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