hugpadhugpad

OpenMOSS-Team / MOSS-SoundEffect-v2.0

Audio1.4B5K153Updated May 26, 2026
Hugging Face

Downloads

5K

Likes

153

Last updated

May 26, 2026

License

apache-2.0

MOSS-SoundEffect v2.0 is a text-to-audio model with a Diffusion Transformer (DiT) backbone trained with the Flow Matching objective, paired with a DAC VAE and a Qwen3 text encoder. It generates high-fidelity environmental, urban, creature, and human-action sound effects from n…

Tasks & library

  • text to audio
  • diffusers

Tags

  • diffusers
  • text-to-audio
  • diffusion
  • flow-matching
  • sound-effects
  • audio-generation

Technical specifications

Parameters1.4B
Librarydiffusers
Languagesen, zh
Base modelQwen/Qwen3-1.7B
Licenseapache-2.0