- Home
- AI Sound Effect Generators
- EzAudio
On the recordRead 9 Oct 202620 facts
EzAudio
On the record
- Access
- The maker links to browser demos for EzAudio and EzAudio-ControlNet, and publishes code and model checkpoints for local use.github.com · read 9 Oct 2026
- Audio editing
- The project describes text to audio generation, audio editing, and inpainting.github.com · read 9 Oct 2026
- Authors and affiliations
- The project page lists Jiarui Hai and coauthors, affiliated with Johns Hopkins University and Tencent AI Lab.haidog-yaqub.github.io · read 9 Oct 2026
- Availability limitation
- The model page says EzAudio is not deployed by an inference provider.huggingface.co · read 9 Oct 2026
- ControlNet
- The repository includes a ControlNet demo and example code that generates audio using a text prompt and an audio reference.github.com · read 9 Oct 2026
- Editing and inpainting
- The project describes support for audio editing and inpainting in addition to text-to-audio generation.github.com · read 9 Oct 2026
- Efficiency
- The paper describes an optimized diffusion transformer designed to improve convergence speed, training stability, and memory usage.haidog-yaqub.github.io · read 9 Oct 2026
- Integrations
- The repository's example code uses PyTorch and SoundFile, and links to model checkpoints hosted on Hugging Face.github.com · read 9 Oct 2026
- License
- The GitHub repository identifies its license as MIT.github.com · read 9 Oct 2026
- Local requirements
- The usage example selects CUDA when available and otherwise uses CPU; installation requires cloning the repository and installing its Python dependencies.github.com · read 9 Oct 2026
- Model design
- EzAudio uses an optimized diffusion transformer for audio latent representations and a one-dimensional waveform variational autoencoder.arxiv.org · read 9 Oct 2026
- Online demos
- The repository links to Hugging Face Spaces for EzAudio and EzAudio-ControlNet demos.github.com · read 9 Oct 2026
- Project page license
- The project website identifies its license as Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International.haidog-yaqub.github.io · read 9 Oct 2026
- Prompt alignment
- The model uses classifier free guidance rescaling to support stronger prompt alignment while preserving audio quality at higher guidance scores.haidog-yaqub.github.io · read 9 Oct 2026
- Prompt guidance
- The paper describes classifier-free guidance rescaling to improve prompt alignment while preserving audio quality at higher guidance scores.arxiv.org · read 9 Oct 2026
- Purpose
- EzAudio is a diffusion based model that generates audio from text prompts.haidog-yaqub.github.io · read 9 Oct 2026
- Release status
- The README lists automatic checkpoint downloading and release of the training pipeline and dataset as todo items.github.com · read 9 Oct 2026
- Training
- The README gives a training command for the text-to-audio diffusion model and points to the SoloAudio work for autoencoder training.github.com · read 9 Oct 2026
