hugpadhugpad

stepfun-ai / Step-Audio-R1.1

Audio33B764192Updated Feb 14, 2026
Hugging Face

Downloads

764

Likes

192

Last updated

Feb 14, 2026

License

apache-2.0

Unlike conventional streaming speech models that trade intelligence for latency, R1.1 enables thinking while speaking, achieving high intelligence without sacrificing speed.

Tasks & library

  • audio text to text
  • transformers

Tags

  • transformers
  • step_audio_2
  • text-generation
  • audio-reasoning
  • chain-of-thought
  • multi-modal

Technical specifications

Parameters33B
Librarytransformers
LanguagesNot available
Licenseapache-2.0