Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Repository Index
47,133 repositories indexed
1–2 of 2 · Most stars
TranslatedMoui (墨忆, Moui, "ink memory") — a lifelike companion agent | Memories written in ink, a heart that grows | based on MaiBot 0.6.3 (GPL-3.0) | Current version: Moui-Mmax