콘텐츠로 이동

ZyphraZonos-v0.1-transformer

Zonos

Conditions Zonos on an eSpeak language code and an authorized speaker reference.

Text to speechVoiceHub-nativezonosParameters: 1.6BLanguages: en, ja +3Training: preprocessedLicense: Checkpoint-specific

Parameter metadata: Exact learned-parameter total for VoiceHub's audited native primary graph at the registered default selection; separately loaded auxiliary models are excluded.

Use this model Checkpoint
Resources
Upstream GitHub VoiceHub source Open in Colab

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: Conditions Zonos on an eSpeak language code and an authorized speaker reference.

Inputs and controls: Tune emotion and sampling only after establishing a deterministic seeded baseline.

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(
    'Zyphra/Zonos-v0.1-transformer',
    model_type='zonos',
    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),
    language="en-us",
    cfg_scale=2.0,
    max_new_tokens=2_048,
)
print(output.file_path, output.sample_rate, output.metadata)

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

Overview

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

Property Value
Task Text to speech
Architecture zonos
Runtime VoiceHub-native
Languages en, ja, zh, fr, de
Capabilities text-to-speech, voice-cloning, multilingual, fine-tuning, safetensors, voicehub-native, native-runtime
Reusable components dac
Normalized output TTSOutput

Language support

Supported language abbreviations

en, ja, zh, fr, de

Paper and GitHub

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('zonos')
print(config.model_type)
Property Value
Canonical model type zonos
Configuration class ZonosConfig
Architecture class ZonosForTextToSpeech

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'Zyphra/Zonos-v0.1-transformer',
    model_type='zonos',
)
print(type(processor).__name__)

Inference

The Usage example returns TTSOutput through AutoModelForTextToSpeech.

Input and output contract

Property Value
Readiness preprocessed
Data architecture codec-lm
Sample rate Model/checkpoint specific
Contract getter get_tts_dataset_spec('zonos')
Variant Required fields One of Boundary Other rules
codec-batch prefix_conditioning, audio_codes — 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 preprocessed
Family causal-lm
Recipe single-phase
Default phase reconstructed_codec_language_model
Training checkpoint Zyphra/Zonos-v0.1-transformer
Native training graph yes
Phase Kind Components Required inputs Loss keys
reconstructed_codec_language_model objective model prefix_conditioning, audio_codes loss, codec_ce_loss

Prepare the exact tensors listed in the data contract before this step. Call model.validate_training_support() first, then follow the training workflow.

Checkpoints, provenance, license, and limitations

Property Value
Default checkpoint Zyphra/Zonos-v0.1-transformer
Hugging Face ID Zyphra/Zonos-v0.1-transformer
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.zonos.modeling_zonos.ZonosForTextToSpeech
Configuration voicehub.models.zonos.configuration_zonos.ZonosConfig
Source provenance voicehub/models/zonos/source/SOURCE.json
License Checkpoint-specific

No VoiceHub-specific license override is registered. Verify the checkpoint and upstream source terms before use.

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

ZonosConfig

View source

ZonosConfig(**config_kwargs)

Parameters

  • **config_kwargs — Configuration fields validated by ZonosConfig.

Model

ZonosForTextToSpeech

View source

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

Parameters

  • pretrained_model_name_or_path — Hub ID or compatible local directory.
  • model_type — Canonical model type; use 'zonos'.
  • config — Optional preloaded ZonosConfig instance.
  • **model_kwargs — Model-specific loading arguments.
from voicehub import get_model_spec

spec = get_model_spec('zonos')
print(spec.display_name, spec.task.value)
Purpose Public object
Discover get_model_spec('zonos')
Load and run AutoModelForTextToSpeech
Configure ZonosConfig
Process AutoProcessor
Model implementation ZonosForTextToSpeech
Normalized output TTSOutput
Training contract get_training_spec('zonos')
Optimization lifecycle available_optimization_passes, apply_optimization_plan, optimization_manifest, restore_optimization_plan

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