AudioLDM: Generate speech, sound effects, music and beyond, with text.

Text-to-Audio Generation

Generate speech, sound effects, music and beyond.

Important tricks to make your generated audio sound better

1. Try to use more adjectives to describe your sound. For example: "A man is speaking clearly and slowly in a professional studio" is better than "A man is speaking". This can make sure AudioLDM understand what you want.
2. Try to use different random seeds, which can affect the generation quality significantly sometimes.
3. It's best to use general terms like 'man' or 'woman' instead of specific names for individuals or abstract objects that humans may not be familiar with, such as 'mummy'.

Web APP

1. Prepare running environment

conda create -n audioldm python=3.8; conda activate audioldm
pip3 install audioldm==0.0.6
git clone https://github.com/haoheliu/AudioLDM; cd AudioLDM

2. Start the web application (powered by Gradio)

python3 app.py

3. A link will be printed out. Click the link to open the browser and play.

Commandline Usage

1. Prepare running environment

# Optional
conda create -n audioldm python=3.8; conda activate audioldm
# Install AudioLDM
pip3 install audioldm==0.0.6

2. text-to-audio generation

# Test run
audioldm -t "A hammer is hitting a wooden surface"

For more options on guidance scale, batchsize, seed, etc, please run

audioldm -h

For the evaluation of audio generative model, please refer to audioldm_eval.

Web Demo

Integrated into Hugging Face Spaces 🤗 using Gradio. Try out the Web Demo

TODO

• Update the checkpoint with more training steps.
• Add AudioCaps finetuned AudioLDM-S model
• Build pip installable package for commandline use
• Build Gradio web application
• Add text-guided style transfer
• Add audio super-resolution
• Add audio inpainting

Cite this work

If you found this tool useful, please consider citing

@article{liu2023audioldm,
  title={AudioLDM: Text-to-Audio Generation with Latent Diffusion Models},
  author={Liu, Haohe and Chen, Zehua and Yuan, Yi and Mei, Xinhao and Liu, Xubo and Mandic, Danilo and Wang, Wenwu and Plumbley, Mark D},
  journal={arXiv preprint arXiv:2301.12503},
  year={2023}
}

Hardware requirement

• GPU with 8GB of dedicated VRAM
• A system with a 64-bit operating system (Windows 7, 8.1 or 10, Ubuntu 16.04 or later, or macOS 10.13 or later) 16GB or more of system RAM

Reference

Part of the code is borrowed from the following repos. We would like to thank the authors of these repos for their contribution.

https://github.com/LAION-AI/CLAP

https://github.com/CompVis/stable-diffusion

https://github.com/v-iashin/SpecVQGAN

https://github.com/toshas/torch-fidelity

We build the model with data from AudioSet, Freesound and BBC Sound Effect library. We share this demo based on the UK copyright exception of data for academic research.