Papers › SoundStorm: Efficient Parallel Audio Generation

SoundStorm: Efficient Parallel Audio Generation

16 May 2023arXiv:2305.09636archive 2025-07-28

Zalán Borsos, Matt Sharifi, Damien Vincent, Eugene Kharitonov, Neil Zeghidour, Marco Tagliasacchi

We present SoundStorm, a model for efficient, non-autoregressive audio generation. SoundStorm receives as input the semantic tokens of AudioLM, and relies on bidirectional attention and confidence-based parallel decoding to generate the tokens of a neural audio codec. Compared to the autoregressive generation approach of AudioLM, our model produces audio of the same quality and with higher consistency in voice and acoustic conditions, while being two orders of magnitude faster. SoundStorm generates 30 seconds of audio in 0.5 seconds on a TPU-v4. We demonstrate the ability of our model to scale audio generation to longer sequences by synthesizing high-quality, natural dialogue segments, given a transcript annotated with speaker turns and a short prompt with the speakers' voices.

PaperPDFCodeCode Syntology ran

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 11 code samples: 9 from 3 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 11: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 5 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 9 samples from 3 repositories, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); 2 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.

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. 3 of the 11 samples that ran have no recorded date.

ZhangXInFD/soundstorm-speechtokenizer mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lucidrains/soundstorm-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
nari-labs/dia mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified 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

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 5 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
5ran · violated contract
5ran

Licence: 3 of the 11 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 3 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. 2 samples are listed last, in a group without a repository. “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.

ZhangXInFD/soundstorm-speechtokenizer community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
divisible_by in 33 papers soundstorm_speechtokenizer/soundstorm.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 fingerprinted licence of this copy not recorded · 856d86b39c6005b4 · report fixture: signature numer:int/0/int, denom:int/0/int · returned bool · level recorded, date not recorded
lucidrains/soundstorm-pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
cast_tuple in 58 papers soundstorm_pytorch/trainer.py ran · honoured contract fingerprinted MIT (permissive) · 5cfcc1d3230706ff · report fixture: signature t:int/0/int · returned tuple · level recorded 2026-09-22
xnor soundstorm_pytorch/soundstorm.py ran · violated contract fingerprinted MIT (permissive) · 1ff4da2e5b7c8f30 · report fixture: signature x:bool/0/bool, y:bool/0/bool · returned bool · level recorded 2026-09-22
yes_or_no in 10 papers soundstorm_pytorch/trainer.py ran · violated contract MIT (permissive) · d95562c398a6b25e · report fixture: signature question:str/0/str · returned bool · level recorded 2026-09-22
nari-labs/dia community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
apply_audio_delay dia/audio.py ran Apache-2.0 (permissive) · bd5b74f128417448 · report fixture: signature audio_BxTxC:Tensor/3/int, pad_value:int/0/int, bos_value:int/0/int, precomp:tuple/1/Tensor · returned Tensor · level recorded 2026-09-24
build_delay_indices dia/audio.py ran Apache-2.0 (permissive) · 230a08e2d42ac7f3 · report fixture: signature B:int/0/int, T:int/0/int, C:int/0/int, delay_pattern:list/1/int · returned tuple · level recorded 2026-09-24
build_revert_indices dia/audio.py ran Apache-2.0 (permissive) · 176dd1fda856a295 · report fixture: signature B:int/0/int, T:int/0/int, C:int/0/int, delay_pattern:list/1/int · returned tuple · level recorded 2026-09-25
create_attn_mask dia/state.py ran Apache-2.0 (permissive) · 591485ad5b203f8f · report fixture: signature q_padding_mask_1d:Tensor/2/bool, k_padding_mask_1d:Tensor/2/bool, device:device/0/?, is_causal:bool/0/bool · returned Tensor · level recorded 2026-09-24
custom_scaled_dot_product_attention dia/layers.py ran Apache-2.0 (permissive) · 746349bd1de0b85d · report fixture: signature query:Tensor/4/float, key:Tensor/4/float, value:Tensor/4/float, attn_mask:Tensor/4/bool, scale:float/0/float, is_causal:bool/0/bool, num_gqa_groups:int/0/int · returned Tensor · level recorded 2026-09-24
Repository not located 2 samples, 2 ran (0 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
default in 430 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
repository not located ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded

Tasks

Audio Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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