Papers › Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

23 Jun 2023NeurIPS 2023 11arXiv:2306.15687archive 2025-07-28

Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster. Audio samples can be found in \url{https://voicebox.metademolab.com}.

PaperPDFConference PDFCodeCode 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="2306.15687")

Code

Syntology Ran 10 of 10 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · honoured contract; 3 ran · violated contract; 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: community (archive-listed): 10 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lucidrains/voicebox-pytorch 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

10 samples harvested; 10 ran; 3 honoured the contract we drafted; 0 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.

3ran · honoured contract
3ran · violated contract
1ran · our draft was wrong
3ran

Licence: 0 of the 10 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 lucidrains/voicebox-pytorch. “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.

cast_tuple lucidrains/voicebox-pytorch/voicebox_pytorch/data.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · f70dcb896366697c · report
cast_tuple lucidrains/voicebox-pytorch/voicebox_pytorch/trainer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 5cfcc1d3230706ff · report
collate_one_or_multiple_tensors lucidrains/voicebox-pytorch/voicebox_pytorch/data.py community (archive-listed) ran MIT (permissive) · 0e0470ad1da271f6 · report
default lucidrains/voicebox-pytorch/voicebox_pytorch/attend.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 60fff7c3c400d7ff · report
exists lucidrains/voicebox-pytorch/voicebox_pytorch/attend.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · aa5486a3650902d8 · report
get_optimizer lucidrains/voicebox-pytorch/voicebox_pytorch/optimizer.py community (archive-listed) ran MIT (permissive) · 9354ff16b3840873 · report
identity lucidrains/voicebox-pytorch/voicebox_pytorch/voicebox_pytorch.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · f3232418205f7cbd · report
once lucidrains/voicebox-pytorch/voicebox_pytorch/attend.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 52e10a7d6b0fa036 · report
separate_weight_decayable_params lucidrains/voicebox-pytorch/voicebox_pytorch/optimizer.py community (archive-listed) ran MIT (permissive) · fdc11aefc97f3abb · report
yes_or_no lucidrains/voicebox-pytorch/voicebox_pytorch/trainer.py community (archive-listed) ran · violated contract MIT (permissive) · d95562c398a6b25e · report

Tasks

In-Context LearningSpeech SynthesisText to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALiBiAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDiscriminative Fine-TuningDropoutGPTLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionResidual ConnectionSoftmaxWeight Decay

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