Text-to-Audio/Make-An-Audio
A conditional diffusion probabilistic model that generates high-fidelity audio from text and other modality inputs.
Not currently ranked — collecting fresh signals.
star history
Make-An-Audio is a generative AI system that produces audio from text prompts using latent diffusion models. It employs a prompt-enhanced diffusion approach for conditioning and supports generation from text and video modalities. The repository provides a PyTorch implementation along with pretrained models for audio generation and audio inpainting tasks.
Frequently asked
- What is Text-to-Audio/Make-An-Audio?
- A conditional diffusion probabilistic model that generates high-fidelity audio from text and other modality inputs.
- Is Make-An-Audio open source?
- Yes — Text-to-Audio/Make-An-Audio is open source, released under the MIT license.
- What language is Make-An-Audio written in?
- Text-to-Audio/Make-An-Audio is primarily written in Python.
- How popular is Make-An-Audio?
- Text-to-Audio/Make-An-Audio has 669 stars on GitHub.
- Where can I find Make-An-Audio?
- Text-to-Audio/Make-An-Audio is on GitHub at https://github.com/Text-to-Audio/Make-An-Audio.