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 ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed); named in the paper: 11 samples from 1 repository, 10 ran (8 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 16 samples that ran has no recorded date.

haoheliu/AudioLDM officialmentioned on GitHubpytorchNOASSERTIONSyntology: 10 samples, 6 ran (3 instrument-failed) · 4 unverified report
haoheliu/audioldm_eval mentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (2 instrument-failed) · 1 unverified report
haoheliu/audioldm-training-finetuning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining (arXiv:2308.05734; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 4 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
huggingface/diffusers jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RefDecoder: Enhancing Visual Generation with Conditional Video Decoding (arXiv:2605.15196; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 16 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
2ran; the contract check could not run
9ran
5unverified

Licence: 12 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

haoheliu/AudioLDM official repository 10 samples, 6 ran (3 instrument-failed) · 4 unverified
DiagonalGaussianDistribution in 7 papers audioldm/ldm.py ran licence not identified · pointer only · 2cda99b6def85873 · report fixture: returned DiagonalGaussianDistribution · level recorded 2026-09-22
disabled_train in 172 papers audioldm/ldm.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · violated contract licence of this copy not recorded · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
extract_into_tensor in 33 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64
audioldm/ldm.py ran · our draft was wrong licence not identified · pointer only · 8971042e12016a60 · report fixture: signature a:Tensor/1/float, t:Tensor/1/int, x_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
make_ddim_sampling_parameters in 9 papers audioldm/ldm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence not identified · pointer only · 3ee640131c9d4362 · report fixture: signature alphacums:ndarray/1/float, ddim_timesteps:ndarray/1/int, eta:float/0/float, verbose:bool/0/bool · returned tuple · level recorded 2026-09-22
make_ddim_timesteps in 18 papers audioldm/ldm.py ran · honoured contract licence not identified · pointer only · 0ea4e960ea54514c · report fixture: signature ddim_discr_method:str/0/str, num_ddim_timesteps:int/0/int, num_ddpm_timesteps:int/0/int, verbose:bool/0/bool · returned ndarray · level recorded 2026-09-22
noise_like in 10 papers audioldm/ldm.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence not identified · pointer only · 2d7200ac60d9a4bd · report fixture: signature shape:tuple/1/int, device:str/0/str, repeat:bool/0/bool · returned Tensor · level recorded 2026-09-22
DDIMSampler in 6 papers audioldm/ldm.py unverified licence not identified · pointer only · 332deacf272549e4 · report
DDPM in 15 papers audioldm/ldm.py unverified licence not identified · pointer only · b7521b6c520cc691 · report
DiffusionWrapper in 5 papers audioldm/ldm.py unverified licence not identified · pointer only · bb9a12b66a9694f1 · report
LatentDiffusion audioldm/ldm.py unverified licence not identified · pointer only · 1d0e58f8ba043419 · report
haoheliu/audioldm_eval named in the paper 11 samples, 10 ran (2 instrument-failed) · 1 unverified
clip_bce audioldm_eval/feature_extractors/panns/losses.py ran MIT (permissive) · 97d45ba74474fdfc · report fixture: signature output_dict:dict/0/?, target_dict:dict/0/? · returned Tensor · level recorded 2026-09-25
dynamic_range_compression in 31 papers audioldm_eval/audio/audio_processing.py ran MIT (permissive) here; the stored copy is pointer only · 0b80ec09e3ba47ae · report fixture: signature x:Tensor/2/float, normalize_fun:callable/0/?, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-25
get_loss_func in 26 papers audioldm_eval/feature_extractors/panns/losses.py ran MIT (permissive) · e424ea90cdf3fd97 · report fixture: signature loss_type:str/0/str · returned function · level recorded 2026-09-25
get_mel_from_wav audioldm_eval/audio/tools.py ran MIT (permissive) · af0a67f05ca8144d · report fixture: signature audio:ndarray/1/float, _stft:callable/0/? · returned tuple · level recorded 2026-09-25
griffin_lim in 16 papers audioldm_eval/audio/audio_processing.py ran · our draft was wrong MIT (permissive) · 9f9ec26d4cdfdf7d · report fixture: signature magnitudes:Tensor/3/float, stft_fn:STFT/0/?, n_iters:int/0/int · returned Tensor · level recorded 2026-09-22
interpolate_bilinear_2d_like_tensorflow1x audioldm_eval/feature_extractors/inception3.py ran MIT (permissive) · 21e50186ab33dd24 · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, align_corners:bool/0/bool, method:str/0/str · returned Tensor · level recorded 2026-09-25
load_json in 344 papers audioldm_eval/audio/tools.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 777e661635ced528 · report fixture: signature fname:str/0/str · returned dict · level recorded 2026-09-24
load_module2model audioldm_eval/feature_extractors/melception_audioset.py ran MIT (permissive) · ffc354ebaecde324 · report fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-25
load_pickle in 115 papers audioldm_eval/audio/tools.py ran MIT (permissive) · 78222542af18c6c5 · report fixture: signature fname:str/0/str · returned dict · level recorded 2026-09-25
pad_short_audio audioldm_eval/datasets/load_mel.py ran fingerprinted MIT (permissive) · e0e3ae45a19356fa · report fixture: signature audio:Tensor/3/float, min_samples:int/0/int · returned Tensor · level recorded 2026-09-25
load_npy_data audioldm_eval/datasets/load_mel.py unverified MIT (permissive) · 98e449b3a6b45350 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AudioLDM (graph method: AudioLDM). 17 bricks; individually on a fixture: 12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 3 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. LatentDiffusion entry · level 0 · unverified · 1d0e58f8ba043419
  2. DDIMSampler helper · level 0 · unverified · 332deacf272549e4
  3. DDPM helper · level 0 · unverified · b7521b6c520cc691
  4. DiagonalGaussianDistribution helper · level 1 · ran · 2cda99b6def85873
  5. default helper · level 1 · ran · violated contract · fbf9ec7be545688e
  6. disabled_train helper · level 1 · ran · violated contract · 4cb732f513d69dfd
  7. instantiate_from_config helper · level 0 · unverified · ef52d142b2c30ac2
  8. noise_like helper · level 1 · ran; the contract check could not run (RAISES) · 2d7200ac60d9a4bd
  9. extract_into_tensor helper · level 1 · ran · our draft was wrong · 8971042e12016a60
  10. make_ddim_sampling_parameters helper · level 1 · ran; the contract check could not run (RAISES) · 3ee640131c9d4362
  11. make_ddim_timesteps helper · level 1 · ran · honoured contract · 0ea4e960ea54514c
  12. DiffusionWrapper helper · level 0 · unverified · bb9a12b66a9694f1
  13. LitEma helper · level 1 · ran · 0f5e41584771596b
  14. count_params helper · level 1 · ran · honoured contract · 613acd72145a95f2
  15. exists helper · level 1 · ran · violated contract · 608e364a9d2376a3
  16. make_beta_schedule helper · level 1 · ran · honoured contract · 3bd7e0cdbd131fdb
  17. get_obj_from_str helper · level 1 · ran · our draft was wrong · 221b2d116fdf1032

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2301.12503") returns these assemblies with each brick's role and wiring (how to connect).

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