NeuTTS¶

Uses NeuTTS's required one-of speaker source with the matching reference transcript.

Text to speechVoiceHub-nativeneuttsParameters: 236MLanguage: enTraining: nativeLicense: NeuTTS-Open-License-1.0

Parameter metadata: Exact Safetensors total reported by the Hugging Face model API for the registered default checkpoint, retrieved 2026-08-13.

Use this model Checkpoint

Resources

Usage¶

Complete the VoiceHub installation once, then run this repository-authored example. Model pages intentionally contain no package-install command.

This example is maintained against VoiceHub's public API; it is not copied from an upstream demo or package README.

Model-specific path: Uses NeuTTS's required one-of speaker source with the matching reference transcript.

Inputs and controls: Exactly one of reference audio or reference codes is mandatory for this checkpoint.

from pathlib import Path

from voicehub import AutoModelForTextToSpeech, TTSGenerationConfig

REFERENCE_AUDIO = Path("reference.wav")
REFERENCE_TEXT = "The reference transcript must exactly match the authorized audio."
if not REFERENCE_AUDIO.is_file():
    raise FileNotFoundError(REFERENCE_AUDIO)

model = AutoModelForTextToSpeech.from_pretrained(
    'neuphonic/neutts-2e',
    model_type='neutts',
    device="cuda",
    lazy_load=True,
)
output = model.generate(
    'VoiceHub keeps model integrations explicit and reproducible.',
    generation_config=TTSGenerationConfig(
        seed=42,
        output_file=Path("output.wav"),
    ),
    speaker_audio_path=str(REFERENCE_AUDIO),
    reference_text=REFERENCE_TEXT,
    temperature=0.8,
    top_k=50,
)
print(output.file_path, output.sample_rate, output.metadata)

Use authorized recordings. Verify hardware needs and pin a revision in production.

Overview¶

neutts is a VoiceHub text to speech integration. This page is generated from its registry contract. Open the neutts Colab notebook.

Property	Value
Task	Text to speech
Architecture	`neutts`
Runtime	`VoiceHub-native`
Languages	`en`
Capabilities	`text-to-speech`, `voice-cloning`, `multilingual`, `emotion`, `safetensors`, `fine-tuning`, `default-checkpoint-inference-only`, `raw-audio-training`, `preencoded-code-training`, `voicehub-native`, `native-runtime`
Reusable components	—
Normalized output	`TTSOutput`

Language support¶

Supported language abbreviations

en

Paper and GitHub¶

Paper: No dedicated upstream research paper is published for this integration.
Upstream GitHub: NeuTTS
VoiceHub source: VoiceHub model implementation

Configuration¶

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('neutts')
print(config.model_type)

Property	Value
Canonical model type	`neutts`
Configuration class	`NeuTTSConfig`
Architecture class	`NeuTTSForTextToSpeech`

Processing¶

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'neuphonic/neutts-2e',
    model_type='neutts',
)
print(type(processor).__name__)

Inference¶

The Usage example returns TTSOutput through AutoModelForTextToSpeech.

Input and output contract¶

Property	Value
Readiness	`integrated-raw`
Data architecture	`codec-lm`
Sample rate	Model/checkpoint specific
Contract getter	`get_tts_dataset_spec('neutts')`

Variant	Required fields	One of	Boundary	Other rules
`raw-audio`	`text`	audio / audio_codes	Source	—
`tokenized`	`input_ids`, `labels`	—	Prepared	—

Autoregressive text/audio-token or codec-language-model data. See the data workflow.

Training and optimization¶

Use available_optimization_passes() to discover reversible public passes. Unsupported runtime or hardware fails closed before mutation.

Training contract¶

Property	Value
Support	`native`
Family	`causal-lm`
Recipe	`single-phase`
Default phase	`codec_language_model`
Training checkpoint	`neuphonic/neutts-air`
Native training graph	`yes`

Phase	Kind	Components	Required inputs	Loss keys
`codec_language_model`	objective	`model.backbone`	`input_ids`, `labels`	`loss`

The integration accepts its declared source or prepared contract directly. Call model.validate_training_support() first, then follow the training workflow.

Checkpoints, provenance, license, and limitations¶

Property	Value
Default checkpoint	`neuphonic/neutts-2e`
Hugging Face ID	`neuphonic/neutts-2e` Repository availability verified through the Hugging Face model API on 2026-08-11; pin a revision before production use.
Checkpoint status	Registry default; pin an immutable revision for production and reproducible evidence
Optional dependency extra	Core package
Hardware and runtime	Usage selects `cuda`; verify checkpoint-specific requirements
Real-checkpoint evidence	Release evidence; a registry default alone is not execution evidence
Implementation	`voicehub.models.neutts.modeling_neutts.NeuTTSForTextToSpeech`
Configuration	`voicehub.models.neutts.configuration_neutts.NeuTTSConfig`
Source provenance	`voicehub/models/neutts/source/SOURCE.json`
License	NeuTTS-Open-License-1.0

NeuTTS Air is Apache-2.0. Other registered variants use the NeuTTS Open License v1.0, which allows limited commercial use below its USD 5,000,000 annual-revenue threshold and requires a separate license at or above that threshold. Commercial use: review required.

Confirm the checkpoint revision, access terms, provenance, and license.

Limitations¶

No integration-specific checkpoint limitation is registered. Verify the selected checkpoint revision and its documented runtime requirements.
Validate memory, precision, and optional dependencies on the target system.
Public optimizations fail closed when the runtime or hardware cannot satisfy their validation contract; an unavailable pass is not reported as applied.
Contract tests do not replace the linked released-checkpoint evidence.

Public API¶

Use the stable configuration, processor, and task-model facades below.

Configuration

`NeuTTSConfig`¶

View source

NeuTTSConfig(**config_kwargs)

Parameters¶

**config_kwargs — Configuration fields validated by NeuTTSConfig.

Model

`NeuTTSForTextToSpeech`¶

View source

AutoModelForTextToSpeech.from_pretrained(
    pretrained_model_name_or_path,
    *,
    model_type='neutts',
    config=None,
    **model_kwargs,
)

Parameters¶

pretrained_model_name_or_path — Hub ID or compatible local directory.
model_type — Canonical model type; use 'neutts'.
config — Optional preloaded NeuTTSConfig instance.
**model_kwargs — Model-specific loading arguments.

from voicehub import get_model_spec

spec = get_model_spec('neutts')
print(spec.display_name, spec.task.value)

Purpose	Public object
Discover	`get_model_spec('neutts')`
Load and run	`AutoModelForTextToSpeech`
Configure	`NeuTTSConfig`
Process	`AutoProcessor`
Model implementation	`NeuTTSForTextToSpeech`
Normalized output	`TTSOutput`
Training contract	`get_training_spec('neutts')`
Optimization lifecycle	`available_optimization_passes`, `apply_optimization_plan`, `optimization_manifest`, `restore_optimization_plan`

See all model guides, inference, and the training matrix.

Usage¶

Overview¶

Language support¶

Paper and GitHub¶

Configuration¶

Processing¶

Inference¶

Input and output contract¶

Training and optimization¶

Training contract¶

Checkpoints, provenance, license, and limitations¶

Limitations¶

Public API¶

NeuTTSConfig¶

Parameters¶

NeuTTSForTextToSpeech¶

Parameters¶

`NeuTTSConfig`¶

`NeuTTSForTextToSpeech`¶