コンテンツにスキップ

QwenQwen3-TTS-12Hz-1.7B-CustomVoice

Qwen3TTS

Uses the registered Qwen3-TTS CustomVoice role with an explicit language and speaker.

Text to speechVoiceHub-nativeqwen3-ttsParameters: 1.9BLanguages: zh, en +8Training: 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
Paper 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 registered Qwen3-TTS CustomVoice role with an explicit language and speaker.

Inputs and controls: Checkpoint roles are not interchangeable; voice cloning requires a Base checkpoint and paired reference fields.

from pathlib import Path

from voicehub import AutoModelForTextToSpeech, TTSGenerationConfig

model = AutoModelForTextToSpeech.from_pretrained(
    'Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice',
    model_type='qwen3tts',
    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"),
    ),
    mode="custom_voice",
    language="English",
    speaker="Vivian",
)
print(output.file_path, output.sample_rate, output.metadata)

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

Overview

qwen3tts is a VoiceHub text to speech integration. This page is generated from its registry contract. Open the qwen3tts Colab notebook.

Property Value
Task Text to speech
Architecture qwen3-tts
Runtime VoiceHub-native
Languages zh, en, ja, ko, … complete audited list below
Capabilities text-to-speech, voice-cloning, voice-design, multilingual, fine-tuning, lora-fine-tuning, default-checkpoint-inference-only, safetensors, voicehub-native, native-runtime
Reusable components —
Normalized output TTSOutput

Language support

Supported language abbreviations

zh, en, ja, ko, de, fr, ru, pt, es, it

Paper and GitHub

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('qwen3tts')
print(config.model_type)
Property Value
Canonical model type qwen3tts
Configuration class Qwen3TTSConfig
Architecture class Qwen3TTSForTextToSpeech

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice',
    model_type='qwen3tts',
)
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('qwen3tts')
Variant Required fields One of Boundary Other rules
single-speaker-sft text, audio_codes, ref_audio — Prepared —
model-ready input_ids, codec_ids, ref_mels, text_embedding_mask, codec_embedding_mask, attention_mask, codec_0_labels, codec_mask — 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 Qwen/Qwen3-TTS-12Hz-1.7B-Base
Native training graph yes
Phase Kind Components Required inputs Loss keys
codec_language_model objective model.model.talker input_ids, codec_ids, ref_mels, text_embedding_mask, codec_embedding_mask, attention_mask, codec_0_labels, codec_mask loss, talker_loss, sub_talker_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 Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Hugging Face ID Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
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.qwen3tts.modeling_qwen3tts.Qwen3TTSForTextToSpeech
Configuration voicehub.models.qwen3tts.configuration_qwen3tts.Qwen3TTSConfig
Source provenance voicehub/models/qwen3tts/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

Qwen3TTSConfig

View source

Qwen3TTSConfig(**config_kwargs)

Parameters

  • **config_kwargs — Configuration fields validated by Qwen3TTSConfig.

Model

Qwen3TTSForTextToSpeech

View source

AutoModelForTextToSpeech.from_pretrained(
    pretrained_model_name_or_path,
    *,
    model_type='qwen3tts',
    config=None,
    **model_kwargs,
)

Parameters

  • pretrained_model_name_or_path — Hub ID or compatible local directory.
  • model_type — Canonical model type; use 'qwen3tts'.
  • config — Optional preloaded Qwen3TTSConfig instance.
  • **model_kwargs — Model-specific loading arguments.
from voicehub import get_model_spec

spec = get_model_spec('qwen3tts')
print(spec.display_name, spec.task.value)
Purpose Public object
Discover get_model_spec('qwen3tts')
Load and run AutoModelForTextToSpeech
Configure Qwen3TTSConfig
Process AutoProcessor
Model implementation Qwen3TTSForTextToSpeech
Normalized output TTSOutput
Training contract get_training_spec('qwen3tts')
Optimization lifecycle available_optimization_passes, apply_optimization_plan, optimization_manifest, restore_optimization_plan

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