No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from OpenMOSS-Team/MOSS-SoundEffect-v2.0
All models by OpenMOSS-Team β
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 natural-language prompts, with controllable duration up to 30 seconds at 48 kHz.
Within the MOSS-TTS Family, MOSS-SoundEffect is the dedicated text-to-sound model β the family member that turns natural-language captions into non-speech audio (ambience, urban scenes, creatures, human actions, short music-like clips). v2.0 supersedes the v1 discrete-token autoregressive backbone (MossTTSDelay) with a continuous-latent Diffusion Transformer + Flow Matching design.
Recommended inference hyperparameters
We recommend a clean, isolated Python 3.12 environment to avoid dependency conflicts with the top-level MOSS-TTS environment.
For a minimal inference-only install (still ships the Gradio demo; skips the fine-tuning extras):
The underlying DiT is wrapped with
torch.compile+ Triton CUDA Graph. The first call may take a few minutes to compile. If you hitTorchDynamo/ Triton errors, setTORCHDYNAMO_DISABLE=1before launching Python.
For a Gradio demo and fine-tuning recipes, see the GitHub README.
conda create -n moss-soundeffect-v2 python=3.12 -yconda activate moss-soundeffect-v2
git clone https://github.com/OpenMOSS/MOSS-TTS.gitcd MOSS-TTS/moss_soundeffect_v2pip install --extra-index-url https://download.pytorch.org/whl/cu128 \ -e ".[torch-cu128,finetune]"pip install --extra-index-url https://download.pytorch.org/whl/cu128 \ -e ".[torch-cu128]"import torchfrom moss_soundeffect_v2 import MossSoundEffectPipeline
pipe = MossSoundEffectPipeline.from_pretrained( "OpenMOSS-Team/MOSS-SoundEffect-v2.0", # this repo, or a local dir torch_dtype=torch.bfloat16, device="cuda",)
audio = pipe( prompt="A dog barking loudly in a park.", seconds=10, num_inference_steps=100, cfg_scale=4.0,) # (B, C, T) waveform tensorpipe.save_audio(audio, "out.wav")