Papers › Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for...

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

1 Jun 2023arXiv:2306.00814archive 2025-07-28

Hubert Siuzdak

Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations, resulting in reduntant and computionally-intensive upsampling operations. Fourier-based time-frequency representation is an appealing alternative, aligning more accurately with human auditory perception, and benefitting from well-established fast algorithms for its computation. Nevertheless, direct reconstruction of complex-valued spectrograms has been historically problematic, primarily due to phase recovery issues. This study seeks to close this gap by presenting Vocos, a new model that directly generates Fourier spectral coefficients. Vocos not only matches the state-of-the-art in audio quality, as demonstrated in our evaluations, but it also substantially improves computational efficiency, achieving an order of magnitude increase in speed compared to prevailing time-domain neural vocoding approaches. The source code and model weights have been open-sourced at https://github.com/gemelo-ai/vocos.

PaperPDFCodeCode Syntology ran

In Syntology 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="2306.00814")

Code

Syntology Ran 5 of 16 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 4 ran; community (archive-listed): 9 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gemelo-ai/vocos officialmentioned in papermentioned on GitHubpytorchMIT report
collabora/whisperspeech mentioned on GitHubpytorchMIT report
whisperspeech/whisperspeech mentioned on GitHubpytorch 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

16 samples harvested; 5 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran
11unverified

Licence: 0 of the 16 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. “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.

gradient_norm gemelo-ai/vocos/vocos/helpers.py official repository ran MIT (permissive) · e4db9b5f77eb31d1 · report
safe_log gemelo-ai/vocos/vocos/modules.py official repository ran fingerprinted MIT (permissive) · 5923f41e711c0b69 · report
symexp gemelo-ai/vocos/vocos/modules.py official repository ran fingerprinted MIT (permissive) · f1abe87534e9b4b5 · report
symlog gemelo-ai/vocos/vocos/modules.py official repository ran fingerprinted MIT (permissive) · 3acb919a94ac1a19 · report
instantiate_class gemelo-ai/vocos/vocos/pretrained.py official repository unverified MIT (permissive) · 72b5e0a028285276 · report
plot_spectrogram_to_numpy gemelo-ai/vocos/vocos/helpers.py official repository unverified MIT (permissive) · e9b4eebcade00ef9 · report
save_figure_to_numpy gemelo-ai/vocos/vocos/helpers.py official repository unverified MIT (permissive) · 4ad86e574a34c6ea · report
singleton IAHispano/Applio/rvc/configs/config.py community (archive-listed) ran MIT (permissive) · 673da1d74b51ce33 · report
discriminator_loss IAHispano/Applio/rvc/train/losses.py community (archive-listed) unverified MIT (permissive) · 0f0065f33f3576c1 · report
feature_loss IAHispano/Applio/rvc/train/losses.py community (archive-listed) unverified MIT (permissive) · 0f7c6286a8d000f3 · report
generator_loss IAHispano/Applio/rvc/train/losses.py community (archive-listed) unverified MIT (permissive) · 613934173d2bad09 · report
max_vram_gpu IAHispano/Applio/rvc/configs/config.py community (archive-listed) unverified MIT (permissive) · 863d1ef3ea0fcbfc · report
phase_vocoder IAHispano/Applio/rvc/realtime/core.py community (archive-listed) unverified MIT (permissive) · af431714735c52d1 · report
run_batch_infer_script IAHispano/Applio/core.py community (archive-listed) unverified MIT (permissive) · c36b80b90b12e1a0 · report
run_infer_script IAHispano/Applio/core.py community (archive-listed) unverified MIT (permissive) · 853b96f40584a36f · report
run_tts_script IAHispano/Applio/core.py community (archive-listed) unverified MIT (permissive) · 2aead06300268e7c · report

Tasks

Audio SynthesisComputational EfficiencyInductive BiasSpeech Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Synthesis LibriTTS Vocos PESQ 3.70 #10 of 15 Archive leaderboard report
Speech Synthesis LibriTTS Vocos Periodicity 0.101 #10 of 15 Archive leaderboard report
Speech Synthesis LibriTTS Vocos V/UV F1 0.9582 #10 of 15 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.

Methods

SPEED

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