Massively Multilingual Speech (MMS) project by Meta combines wav2vec 2.0 and a new dataset to provide labeled data for over 1,100 languages and unlabeled data for nearly 4,000 languages. The MMS models outperform existing models and cover 10 times as many languages. The project aims to make a small contribution to preserve the incredible language diversity of the world. MMS supports speech-to-text and text-to-speech for 1,107 languages and language identification for over 4,000 languages.