Skip to main content
Rase AI Intelligence Newsletter

Creative AI Model or AI service

Nari Labs’ Dia synthesizes multi-speaker dialogue from a script

Dia is Nari Labs’ text-to-speech model for generating dialogue from written turns. [1]

What the model does

The model card describes marking different speakers in a script and generating nonverbal sounds such as laughter. [1]

Why it matters

A single dialogue model gives a producer a way to prototype the timing and interaction between multiple scripted voices. [1]

Sources and verification

Catalog evidence checked How we verify records

  1. Primary source nari-labs/Dia-1.6B

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