콘텐츠로 이동

OuteAILlama-OuteTTS-1.0-1B

OuteTTS

Uses the audited OuteTTS V3 regular generation path with an explicit token limit.

Text to speechVoiceHub-nativeoutettsParameters: 1.2BLanguages: en, ar +21Training: preprocessedLicense: CC-BY-NC-SA-4.0

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
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: Uses the audited OuteTTS V3 regular generation path with an explicit token limit.

Inputs and controls: Speaker profiles are optional; add one only if it matches the selected V3 checkpoint protocol.

from pathlib import Path

from voicehub import AutoModelForTextToSpeech, TTSGenerationConfig

model = AutoModelForTextToSpeech.from_pretrained(
    'OuteAI/Llama-OuteTTS-1.0-1B',
    model_type='outetts',
    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"),
    ),
    generation_type="regular",
    max_length=1_024,
)
print(output.file_path, output.sample_rate, output.metadata)

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

Overview

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

Property Value
Task Text to speech
Architecture outetts
Runtime VoiceHub-native
Languages en, ar, zh, nl, … complete audited list below
Capabilities text-to-speech, voice-cloning, fine-tuning, safetensors, voicehub-native, native-runtime, preprocessed-training, speaker-profile-training
Reusable components dac
Normalized output TTSOutput

Language support

Supported language abbreviations

en, ar, zh, nl, fr, de, it, ja, ko, lt, ru, es, pt, be, bn, ka, hu, lv, fa, pl, sw, ta, uk

Paper and GitHub

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('outetts')
print(config.model_type)
Property Value
Canonical model type outetts
Configuration class OuteTTSConfig
Architecture class OuteTTSForTextToSpeech

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'OuteAI/Llama-OuteTTS-1.0-1B',
    model_type='outetts',
)
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 24,000 Hz
Contract getter get_tts_dataset_spec('outetts')
Variant Required fields One of Boundary Other rules
v3-profile — speaker_profile / speaker / profile Prepared —
inline-v3-profile text, words, global_features — Prepared —
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 preprocessed
Family causal-lm
Recipe single-phase
Default phase codec_language_model
Training checkpoint OuteAI/Llama-OuteTTS-1.0-1B
Native training graph yes
Phase Kind Components Required inputs Loss keys
codec_language_model objective model.language_model input_ids, labels 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 OuteAI/Llama-OuteTTS-1.0-1B
Hugging Face ID OuteAI/Llama-OuteTTS-1.0-1B
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.outetts.modeling_outetts.OuteTTSForTextToSpeech
Configuration voicehub.models.outetts.configuration_outetts.OuteTTSConfig
Source provenance voicehub/models/outetts/source/SOURCE.json
License CC-BY-NC-SA-4.0

The default Llama-OuteTTS-1.0-1B checkpoint is non-commercial. The supported OuteTTS 0.6B checkpoint is Apache-2.0; review the selected artifact before training or deployment. Commercial use: not allowed.

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

OuteTTSConfig

View source

OuteTTSConfig(**config_kwargs)

Parameters

  • **config_kwargs — Configuration fields validated by OuteTTSConfig.

Model

OuteTTSForTextToSpeech

View source

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

Parameters

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

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

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