Stability-AI/stable-audio-tools
Training and inference toolkit for conditional audio generation models from Stability AI.
Not currently ranked — collecting fresh signals.
star history
This repository provides code for training and running generative audio models. It supports PyTorch 2.5 with Flash Attention optimization and offers both programmatic APIs and a Gradio web interface for testing pretrained models such as stable-audio-open-1.0. Users can train custom audio generation models or run inference on existing checkpoints from Hugging Face.
Frequently asked
- What is Stability-AI/stable-audio-tools?
- Training and inference toolkit for conditional audio generation models from Stability AI.
- Is stable-audio-tools open source?
- Yes — Stability-AI/stable-audio-tools is open source, released under the MIT license.
- What language is stable-audio-tools written in?
- Stability-AI/stable-audio-tools is primarily written in Python.
- How popular is stable-audio-tools?
- Stability-AI/stable-audio-tools has 3.8k stars on GitHub.
- Where can I find stable-audio-tools?
- Stability-AI/stable-audio-tools is on GitHub at https://github.com/Stability-AI/stable-audio-tools.