Skip to main content
Rase AI Intelligence Newsletter

Creative AI Model or AI service

Step-Audio brings speech and dialogue into one research project

StepFun released the Step-Audio research artifacts for spoken interaction, including a conversational model and speech-generation components. [1][2]

What the model does

The February release includes separate conversational, speech-synthesis and audio-tokenization artifacts, along with an evaluation benchmark for multi-turn conversations. [1][2]

Why it matters

The published artifacts let speech researchers evaluate conversational audio with the project's own benchmark and distinguish it from separate speech generation work. [1][2]

Key dates

  1. StepFun publishes Step-Audio research artifacts [1]

Model limitations

The dated milestone is the publication of research artifacts. [1][2]

Sources and verification

Catalog evidence checked How we verify records

  1. Primary source StepFun project’s Step-Audio release notes
  2. Primary source stepfun-ai/Step-Audio-Chat

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