Skip to main content
Rase AI Intelligence Newsletter

Creative AI Model or AI service

Kyutai’s Moshi models simultaneous listening and speaking

Moshi is a speech and text model from Kyutai designed for spoken dialogue in which both sides can speak over one another. [1]

What the model does

The model handles its own audio and the listener’s audio in parallel streams, allowing it to track speech while it is producing a response. [1]

Why it matters

This structure gives researchers a way to study interruptions and overlapping turns in voice interfaces. [1]

Sources and verification

Catalog evidence checked How we verify records

  1. Primary source kyutai/moshiko-pytorch-bf16

Related profiles

Creative AI

Seedance 2.5 (4K API and Flash)

ByteDance (Volcano Engine / BytePlus)

These tools generate video through developer services. The cited sources describe different variants and routes of access.

Medium confidenceEvidence checked

Creative AI

LongCat-Video-Avatar 1.6

Meituan (LongCat team)

It generates video of an avatar from supported inputs in the documented project.

High confidenceEvidence checked

Creative AI

MiniMax H3-Image

MiniMax

It generates images from prompts through the model architecture described by MiniMax.

High confidenceEvidence checked