# Multilingual speech support

WavTokenizer is a model for speech processing, supporting 75-token speech encoding.

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

VoiceCraft is a high-quality text-to-speech model that supports zero-shot speech synthesis and editing.

Mossi text-to-speech model developed by Meta, based on VITS architecture, supporting end-to-end speech synthesis

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

The Lampung Api text-to-speech model developed by Meta, which is part of the MMS multilingual speech project

A Chin and Bam text-to-speech model developed by Meta, part of the Massively Multilingual Speech (MMS) project.

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

Khmer text-to-speech model from Facebook's MMS project, implemented with VITS architecture for end-to-end speech synthesis

A Bambara text-to-speech model developed by Meta, part of the Massively Multilingual Speech project, utilizing the VITS architecture for high-quality speech synthesis.

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

North Azerbaijani (Latin script) text-to-speech model developed by Meta, part of the Massively Multilingual Speech project

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

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

Oromo text-to-speech model from Facebook's MMS project, implementing end-to-end speech synthesis based on VITS architecture

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

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

Amis text-to-speech model developed by Meta, supporting end-to-end speech synthesis

VITS architecture Lao TTS model developed by Meta, supporting end-to-end speech synthesis

A Fula text-to-speech model developed by Meta as part of the Massively Multilingual Speech project, supporting the conversion of Fula text into natural speech.

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

Indonesian text-to-speech model from Facebook's MMS project, implemented with VITS architecture for end-to-end speech synthesis

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

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

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

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

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

A Maithili text-to-speech model developed by Meta, part of the Massively Multilingual Speech (MMS) project, supporting speech synthesis for Maithili (mai).