Text-to-Audio
MLX
Safetensors
Chinese
English
audio
sound-effects
audio-generation
apple-silicon
quantized
4bit
Instructions to use appautomaton/openmoss-sound-effect-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use appautomaton/openmoss-sound-effect-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir openmoss-sound-effect-mlx appautomaton/openmoss-sound-effect-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
OpenMOSS SoundEffect โ MLX 4-bit
MLX-native 4-bit conversion of OpenMOSS SoundEffect for local text-to-audio generation on Apple Silicon.
Variants
| Path | Precision |
|---|---|
mlx-4bit/ |
4-bit quantized weights |
How to Get Started
python scripts/generate/moss_sound_effect.py \
--ambient-sound "rolling thunder with steady rainfall on a metal roof" \
--duration-seconds 8 \
--output outputs/thunder.wav
Duration controls the expected token budget at 12.5 tokens/second.
Model Details
- Upstream model:
OpenMOSS-Team/MOSS-SoundEffect - Task: text-to-audio and sound-effect generation
- Runtime: MLX on Apple Silicon
Links
- Source code: mlx-speech
License
Apache 2.0 โ following the upstream license published with OpenMOSS-Team/MOSS-SoundEffect.
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for appautomaton/openmoss-sound-effect-mlx
Base model
OpenMOSS-Team/MOSS-SoundEffect