# Multilingual speech technology

The Runyoro text-to-speech model developed by Meta, which is part of the Massive Multilingual Speech (MMS) project

A text-to-speech model for Trinidadian Creole developed by Meta, which uses the VITS architecture to achieve high-quality speech synthesis.

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

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

A Romani-Carpathian dialect text-to-speech model developed by Meta, part of the Massively Multilingual Speech (MMS) project

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

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

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

Northern Kurdish text-to-speech model developed by Meta, supporting speech synthesis for Northern Kurdish written in Arabic script

Urdu text-to-speech model developed by Meta, supporting Arabic script input, part of the MMS multilingual speech project

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