Seamless

Text-to-Audio

Seamless is a MMMMT (Massively Multilingual and Multimodal Machine Translation) model that can translate and generate audio in over 100 languages.

Seamless is distributed under a CC-BY-NC 4.0 License, and cannot be utilized for commercial purposes. You are permitted to download and run this model onto a cloud server and/or onto your local computer for research purposes.

Information Links

Research how the model was created and how it should be utilized.

Compatible Open Source Apps

Community-built web applications to run the model.