Higgs Audio is our family of foundation audio and avatar models. They generate natural speech, recognize speech in many languages, clone a voice from a short sample, detect sentiment, and give a voice a face.
Our Higgs models listen, speak, and see. Higgs Realtime is a speech-to-speech API with tool calling and support for 100+ languages, and it is drop-in compatible with the OpenAI Realtime API.
Our Higgs models listen, speak, and see. Higgs Realtime is a speech-to-speech API with tool calling and support for 100+ languages, and it is drop-in compatible with the OpenAI Realtime API.
Not enough roles to summarise yet.
Canada
Santa Clara HQ, USA