xcc-zach/xtalk

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.

Native End-to-End Full-Duplex Spoken Language Model

[EMNLP 2026 Main] Speaking While Listening: a survey and empirical audit of full-duplex spoken dialogue systems — L0–L3 architectural hierarchy, T×I×R interaction ontology, and a five-state decision machine, with a curated list of models, datasets, and benchmarks.

J-Moshi: A Japanese Full-duplex Spoken Dialogue System

S.T.A.R.K. - Speech And Text Algorithmic Recognition Kit

MichiAI: A Low Latency, Full Duplex Speech LLM with zero coherence loss

A curated list of full-duplex spoken dialogue models & benchmarks

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.