Papers › AudioLDM: Text-to-Audio Generation with Latent Diffusion Models

AudioLDM: Text-to-Audio Generation with Latent Diffusion Models

29 Jan 2023arXiv:2301.12503archive 2025-07-28

Haohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei, Xubo Liu, Danilo Mandic, Wenwu Wang, Mark D. Plumbley

Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents. The pretrained CLAP models enable us to train LDMs with audio embedding while providing text embedding as a condition during sampling. By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance measured by both objective and subjective metrics (e.g., frechet distance). Moreover, AudioLDM is the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2301.12503")

Code

Syntology Ran 15 of 21 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 5 ran; named in the paper: 11 samples from 1 repository, 9 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

haoheliu/AudioLDM officialmentioned on GitHubpytorchNOASSERTION report
haoheliu/audioldm_eval mentioned in papermentioned on GitHubpytorchMIT report
haoheliu/audioldm-training-finetuning mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

21 samples harvested; 15 ran; 1 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
9ran
6unverified

Licence: 10 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DiagonalGaussianDistribution haoheliu/AudioLDM/audioldm/ldm.py official repository ran licence not identified · pointer only · 2cda99b6def85873 · report
extract_into_tensor haoheliu/AudioLDM/audioldm/ldm.py official repository ran · our draft was wrong licence not identified · pointer only · 8971042e12016a60 · report
make_ddim_sampling_parameters haoheliu/AudioLDM/audioldm/ldm.py official repository ran · fixture could not drive it licence not identified · pointer only · 3ee640131c9d4362 · report
make_ddim_timesteps haoheliu/AudioLDM/audioldm/ldm.py official repository ran · honoured contract licence not identified · pointer only · 0ea4e960ea54514c · report
noise_like haoheliu/AudioLDM/audioldm/ldm.py official repository ran · fixture could not drive it licence not identified · pointer only · 2d7200ac60d9a4bd · report
DDIMSampler haoheliu/AudioLDM/audioldm/ldm.py official repository unverified licence not identified · pointer only · 332deacf272549e4 · report
DDPM haoheliu/AudioLDM/audioldm/ldm.py official repository unverified licence not identified · pointer only · b7521b6c520cc691 · report
DiffusionWrapper haoheliu/AudioLDM/audioldm/ldm.py official repository unverified licence not identified · pointer only · bb9a12b66a9694f1 · report
LatentDiffusion haoheliu/AudioLDM/audioldm/ldm.py official repository unverified licence not identified · pointer only · 1d0e58f8ba043419 · report
clip_bce haoheliu/audioldm_eval/audioldm_eval/feature_extractors/panns/losses.py named in the paper ran MIT (permissive) · 97d45ba74474fdfc · report
get_loss_func haoheliu/audioldm_eval/audioldm_eval/feature_extractors/panns/losses.py named in the paper ran MIT (permissive) · e424ea90cdf3fd97 · report
get_mel_from_wav haoheliu/audioldm_eval/audioldm_eval/audio/tools.py named in the paper ran MIT (permissive) · af0a67f05ca8144d · report
griffin_lim haoheliu/audioldm_eval/audioldm_eval/audio/audio_processing.py named in the paper ran · our draft was wrong MIT (permissive) · 9f9ec26d4cdfdf7d · report
interpolate_bilinear_2d_like_tensorflow1x haoheliu/audioldm_eval/audioldm_eval/feature_extractors/inception3.py named in the paper ran MIT (permissive) · 21e50186ab33dd24 · report
load_json haoheliu/audioldm_eval/audioldm_eval/audio/tools.py named in the paper ran MIT (permissive) · 777e661635ced528 · report
load_module2model haoheliu/audioldm_eval/audioldm_eval/feature_extractors/melception_audioset.py named in the paper ran MIT (permissive) · ffc354ebaecde324 · report
load_pickle haoheliu/audioldm_eval/audioldm_eval/audio/tools.py named in the paper ran MIT (permissive) · 78222542af18c6c5 · report
pad_short_audio haoheliu/audioldm_eval/audioldm_eval/datasets/load_mel.py named in the paper ran fingerprinted MIT (permissive) · e0e3ae45a19356fa · report
dynamic_range_compression haoheliu/audioldm_eval/audioldm_eval/audio/audio_processing.py named in the paper unverified MIT (permissive) · 0b80ec09e3ba47ae · report
load_npy_data haoheliu/audioldm_eval/audioldm_eval/datasets/load_mel.py named in the paper unverified MIT (permissive) · 98e449b3a6b45350 · report
disabled_train identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 4cb732f513d69dfd · report

Tasks

Audio GenerationComputational EfficiencyStyle Transfer

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Generation AudioCaps AudioLDM-L-Full FAD 1.96 #19 of 23 Archive leaderboard report
Audio Generation AudioCaps AudioLDM-L-Full FD 23.31 #19 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections