All tasks / Models

MOSS-SoundEffect v2.0

Open-weights text-to-sound-effects model (1.3B DiT, flow matching) generating 48 kHz effects and ambience up to 30 s from English or Chinese prompts.

  • OpenMOSS team and MOSI.AI
  • Open weights
  • Released 26 May 2026

Official page

Where it ranks

  • –
    Sound effects
    Models · Local · no result on this task’s benchmarks yet

Facts

Vendor
OpenMOSS team and MOSI.AI
Family
MOSS-SoundEffect
Released
26 May 2026
Weights
Open: download and run it yourself
License
Apache-2.0
Access
Free (open weights)
Last verified
19 Oct 2026

Price from huggingface.co, 19 Oct 2026.

Benchmark results

No public benchmark results recorded yet.

Where you can use it

No tracked tool lists this model yet; as open weights it runs in local runtimes.

Earlier versions

  • MOSS-SoundEffect (8B) · Feb 2026

Sources