On August 23, Meta announced the open-source release of SeamlessM4T, a large-scale model capable of translating multiple voices and languages. SeamlessM4T supports translation across 100 languages and voices, enabling multi-modal translation including speech-to-text, speech-to-speech, text-to-speech, and text-to-text. This model integrates previously released translation models by Meta such as NLLB and MMS, and has been trained using 270,000 hours of aligned voice-text data, making it the largest and most comprehensive open-source translation model to date.