SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.02111 · 2023

Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2301.02111.json · badge: /api/ran/2301.02111.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
lifeiteng/vall-e community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_lr Ran
ran on a synthesized input
lifeiteng/vall-e/valle/modules/scheduler.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from 0nutation/uslm, is pointer only (licence: NONE) · get_code("ffec7b2aa35d0253")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from 0nutation/uslm, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

random_cast_to_half Ran
ran; our contract draft was wrong, not the code
lifeiteng/vall-e/valle/modules/scaling.py
code served (permissive licence) · get_code("982b9083b5a41368")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import Tensor

torch.manual_seed(0)

# Create a small floating point tensor with mixed magnitudes
# Some values above min_abs threshold, some below
x = torch.tensor([
    [1e-5, 1e-4, 0.5, -0.3],
    [1e-7, 2e-6, -0.1, 0.2]
], dtype=torch.float32)

ARGS = {
    "x": x,
    "min_abs": 5e-06
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
random_clamp Ran
ran; our contract draft was wrong, not the code
lifeiteng/vall-e/valle/modules/scaling.py
code served (permissive licence) · get_code("1d72f492e19080e6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small tensor for the function to operate on
# Shape: (2, 4) - batch size 2, feature dimension 4
x = torch.randn(2, 4, requires_grad=True)

# Define arguments for random_clamp function
ARGS = {
    'x': x,
    'min': -1.0,
    'max': 1.0,
    'prob': 0.5,
    'reflect': 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
softmax Ran
ran; our contract draft was wrong, not the code
lifeiteng/vall-e/valle/modules/scaling.py
code served (permissive licence) · get_code("c124aa8bd6b9ebe9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import Tensor

torch.manual_seed(0)

# Create a small tensor for softmax computation
# Using shape (2, 4) - batch size 2, dimension 4
x = torch.randn(2, 4, dtype=torch.float32)

# The dim parameter specifies which dimension to apply softmax over
dim = 1

# Map all parameters of the softmax function to their values
ARGS = {
    "x": x,
    "dim": dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
top_k_top_p_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lifeiteng/vall-e/valle/models/valle.py
code served (permissive licence) · get_code("99a311d99448f881")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small logits tensor: batch_size=2, vocab_size=4
logits = torch.randn(2, 4)

ARGS = {
    "logits": logits,
    "top_k": 2,
    "top_p": 0.9,
    "filter_value": -float('Inf'),
    "min_tokens_to_keep": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
topk_sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lifeiteng/vall-e/valle/models/valle.py
code served (permissive licence) · get_code("fb8e21d446dcf26f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family int, shape (2, 1) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create tiny logits tensor: batch_size=2, vocab_size=4
logits = torch.randn(2, 4)

ARGS = {
    'logits': logits,
    'top_k': 2,
    'top_p': 0.9,
    'temperature': 1.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family int, shape (2, 1) — shape (2, 1) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 6 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
top_k_top_p_filtering 21 other papers
10 dated earlier, 11 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
2009.06367 (2020-09)
GeDi: Generative Discriminator Guided Sequence Generation
and 18 more not named here
topk_sampling 4 other papers
4 later
2308.16692 (2023-08)
SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS
2403.16973 (2024-03)
VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild
2409.05356 (2024-09)
INDICVOICES-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
and 1 more not named here
random_cast_to_half 3 other papers
3 later
2303.03926 (2023-03)
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
2308.16692 (2023-08)
SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS
2409.07556 (2024-09)
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
random_clamp 3 other papers
3 later
2303.03926 (2023-03)
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
2308.16692 (2023-08)
SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS
2409.07556 (2024-09)
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
softmax 3 other papers
3 later
2303.03926 (2023-03)
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
2308.16692 (2023-08)
SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS
2409.07556 (2024-09)
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
calc_lr 1 other paper
1 later
2308.16692 (2023-08)
SPEECHTOKENIZER: UNIFIED SPEECH TOKENIZER FOR SPEECH LANGUAGE MODELS

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. See https://aka.ms/valle for demos of our work.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.02111")
get_code_for_paper("2301.02111")
have("2301.02111")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.02111.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.02111.svg)](https://syntology.ai/paper/2301.02111)

Connect an agent — have() is free.