SolfaSolfaThe turn between speaking and listening is not only in language.
Face to face, people rarely rely on complete sentences alone. Meaning, sound, rhythm, expression, gaze, posture, and movement build understanding together. We interrupt, hesitate, glance back, lean in — and change our minds mid-expression.
A robot needs the same coherence across these channels. The moment its words, its gaze, its posture, and its next movement come apart from each other, people can no longer read its real state and intent.
We are training an embodied multimodal real-time interaction model. The model receives speech, not text — it learns the rhythm of speaking and listening, not word meanings.