Edit model card


AudioLDM is a latent text-to-audio diffusion model capable of generating realistic audio samples given any text input. It is available in the 🧨 Diffusers library from v0.15.0 onwards.

Model Details

AudioLDM was proposed in the paper AudioLDM: Text-to-Audio Generation with Latent Diffusion Models by Haohe Liu et al.

Inspired by Stable Diffusion, AudioLDM is a text-to-audio latent diffusion model (LDM) that learns continuous audio representations from CLAP latents. AudioLDM takes a text prompt as input and predicts the corresponding audio. It can generate text-conditional sound effects, human speech and music.

Checkpoint Details

This is the original, small version of the AudioLDM model, also referred to as audioldm-s-full. The four AudioLDM checkpoints are summarised in the table below:

Table 1: Summary of the AudioLDM checkpoints.

Checkpoint Training Steps Audio conditioning CLAP audio dim UNet dim Params
audioldm-s-full 1.5M No 768 128 421M
audioldm-s-full-v2 > 1.5M No 768 128 421M
audioldm-m-full 1.5M Yes 1024 192 652M
audioldm-l-full 1.5M No 768 256 975M

Model Sources


First, install the required packages:

pip install --upgrade diffusers transformers accelerate


For text-to-audio generation, the AudioLDMPipeline can be used to load pre-trained weights and generate text-conditional audio outputs:

from diffusers import AudioLDMPipeline
import torch

repo_id = "cvssp/audioldm"
pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "Techno music with a strong, upbeat tempo and high melodic riffs"
audio = pipe(prompt, num_inference_steps=10, audio_length_in_s=5.0).audios[0]

The resulting audio output can be saved as a .wav file:

import scipy

scipy.io.wavfile.write("techno.wav", rate=16000, data=audio)

Or displayed in a Jupyter Notebook / Google Colab:

from IPython.display import Audio

Audio(audio, rate=16000)



  • Descriptive prompt inputs work best: you can use adjectives to describe the sound (e.g. "high quality" or "clear") and make the prompt context specific (e.g., "water stream in a forest" instead of "stream").
  • It's best to use general terms like 'cat' or 'dog' instead of specific names or abstract objects that the model may not be familiar with.


  • The quality of the predicted audio sample can be controlled by the num_inference_steps argument: higher steps give higher quality audio at the expense of slower inference.
  • The length of the predicted audio sample can be controlled by varying the audio_length_in_s argument.



  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},
Downloads last month
Unable to determine this model’s pipeline type. Check the docs .