{"library":"stable-audio-tools","title":"Stable Audio Tools","type":"library","description":"A Python library by Stability AI for training and inference with generative audio models, including Stable Audio and Dance Diffusion. Current version 0.0.19. Active development with frequent updates.","language":"python","status":"active","last_verified":"Fri May 01","install":{"commands":["pip install stable-audio-tools"],"cli":null},"imports":["from stable_audio_tools import get_models","from stable_audio_tools.interface import create_model_from_config","from stable_audio_tools.interface import ModelConfig","from stable_audio_tools.interface import get_pretrained_model_and_config"],"auth":{"required":false,"env_vars":[]},"links":{"homepage":null,"github":null,"docs":null,"changelog":null,"pypi":"https://pypi.org/project/stable-audio-tools/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null},"quickstart":{"code":"import torch\nimport soundfile as sf\nfrom stable_audio_tools import get_models\nfrom stable_audio_tools.interface import get_pretrained_model_and_config\n\n# List available models\nmodels = get_models()\nprint(\"Available models:\", list(models.keys()))\n\n# Use a stable audio model (replace with actual model name from list)\nmodel_name = \"stable-audio-open-1.0\"  # example, check get_models()\nmodel, config = get_pretrained_model_and_config(model_name)\n\n# Generate audio: text-to-audio (simplified, requires proper sampling setup)\n# Create a random latent and decode (demo only)\ndevice = \"cuda\" if torch.cuda.is_available() else \"cpu\"\nmodel = model.to(device)\n# Note: Full generation requires T5 text encoder and diffusion loop\nprint(\"Model loaded successfully. Refer to official docs for full inference.\")","lang":"python","description":"Quickstart to list models and load a pretrained model. Full text-to-audio generation requires additional steps (text encoder, diffusion loop).","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}