ElevenLabs From $6/mo · Free plan 9.0 Visit 
EzAudio
haidog-yaqub.github.io
Spec sheet
- Purpose
- EzAudio is a diffusion based model that generates audio from text prompts.Read 9 Oct 2026 · haidog-yaqub.github.io
- Integrations
- The repository's example code uses PyTorch and SoundFile, and links to model checkpoints hosted on Hugging Face.Read 9 Oct 2026 · github.com
- License
- The GitHub repository identifies its license as MIT.Read 9 Oct 2026 · github.com
- Founded
- 2024Read 28 Sep 2026 · haidog-yaqub.github.io
- Access
- The maker links to browser demos for EzAudio and EzAudio-ControlNet, and publishes code and model checkpoints for local use.Read 9 Oct 2026 · github.com
- Audio editing
- The project describes text to audio generation, audio editing, and inpainting.Read 9 Oct 2026 · github.com
- Authors and affiliations
- The project page lists Jiarui Hai and coauthors, affiliated with Johns Hopkins University and Tencent AI Lab.Read 9 Oct 2026 · haidog-yaqub.github.io
- Availability limitation
- The model page says EzAudio is not deployed by an inference provider.Read 9 Oct 2026 · huggingface.co
- ControlNet
- The repository includes a ControlNet demo and example code that generates audio using a text prompt and an audio reference.Read 9 Oct 2026 · github.com
- Editing and inpainting
- The project describes support for audio editing and inpainting in addition to text-to-audio generation.Read 9 Oct 2026 · github.com
- Efficiency
- The paper describes an optimized diffusion transformer designed to improve convergence speed, training stability, and memory usage.Read 9 Oct 2026 · haidog-yaqub.github.io
- Local requirements
- The usage example selects CUDA when available and otherwise uses CPU; installation requires cloning the repository and installing its Python dependencies.Read 9 Oct 2026 · github.com
- Model design
- EzAudio uses an optimized diffusion transformer for audio latent representations and a one-dimensional waveform variational autoencoder.Read 9 Oct 2026 · arxiv.org
- Online demos
- The repository links to Hugging Face Spaces for EzAudio and EzAudio-ControlNet demos.Read 9 Oct 2026 · github.com
- Project page license
- The project website identifies its license as Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International.Read 9 Oct 2026 · haidog-yaqub.github.io
- Prompt alignment
- The model uses classifier free guidance rescaling to support stronger prompt alignment while preserving audio quality at higher guidance scores.Read 9 Oct 2026 · haidog-yaqub.github.io
- Prompt guidance
- The paper describes classifier-free guidance rescaling to improve prompt alignment while preserving audio quality at higher guidance scores.Read 9 Oct 2026 · arxiv.org
- Release status
- The README lists automatic checkpoint downloading and release of the training pipeline and dataset as todo items.Read 9 Oct 2026 · github.com
- Training
- The README gives a training command for the text-to-audio diffusion model and points to the SoloAudio work for autoencoder training.Read 9 Oct 2026 · github.com
- Training resources
- The repository's todo list includes releasing the training pipeline and dataset.Read 9 Oct 2026 · github.com
Where Specifiction places it
- AI Sound Effect Generators#22 of 297.3
