> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/QwenLM/Qwen3-TTS/llms.txt
> Use this file to discover all available pages before exploring further.

# Available Models

> Overview of Qwen3-TTS model variants and their capabilities

## Model Overview

Qwen3-TTS offers a family of models optimized for different use cases, from voice cloning to instruction-based voice design. All models are built on the same architecture but are fine-tuned for specific capabilities.

## Model Comparison

| Model                               | Parameters | Features                            | Language Support | Streaming | Instruction Control |
| ----------------------------------- | ---------- | ----------------------------------- | ---------------- | --------- | ------------------- |
| **Qwen3-TTS-12Hz-1.7B-VoiceDesign** | 1.7B       | Voice design from text descriptions | 10 languages     | ✅         | ✅                   |
| **Qwen3-TTS-12Hz-1.7B-CustomVoice** | 1.7B       | 9 premium voices with style control | 10 languages     | ✅         | ✅                   |
| **Qwen3-TTS-12Hz-1.7B-Base**        | 1.7B       | 3-second voice cloning              | 10 languages     | ✅         | ❌                   |
| **Qwen3-TTS-12Hz-0.6B-CustomVoice** | 0.6B       | 9 premium voices                    | 10 languages     | ✅         | ❌                   |
| **Qwen3-TTS-12Hz-0.6B-Base**        | 0.6B       | 3-second voice cloning              | 10 languages     | ✅         | ❌                   |

**Supported Languages**: Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian

## Model Variants

<CardGroup cols={2}>
  <Card title="VoiceDesign" icon="palette" iconType="duotone">
    Create custom voices from natural language descriptions
  </Card>

  <Card title="CustomVoice" icon="microphone" iconType="duotone">
    Use 9 premium pre-trained voices with style control
  </Card>

  <Card title="Base" icon="clone" iconType="duotone">
    Clone any voice from just 3 seconds of audio
  </Card>

  <Card title="Tokenizer" icon="waveform-lines" iconType="duotone">
    Encode/decode audio for compression and transport
  </Card>
</CardGroup>

### 1. Qwen3-TTS-12Hz-1.7B-VoiceDesign

**Best for**: Creating unique voices based on detailed descriptions

<Tabs>
  <Tab title="Capabilities">
    * Generate voices from natural language descriptions
    * Control timbre, age, gender, emotion, and speaking style
    * Instruction-based prosody and tone adjustment
    * Adaptive emotional expression based on text semantics
    * Streaming generation support
  </Tab>

  <Tab title="Use Cases">
    * Character voice creation for games and animation
    * Personalized virtual assistants
    * Content creation requiring unique voices
    * Prototyping voice concepts without recording
  </Tab>

  <Tab title="Example">
    ```python theme={null}
    from qwen_tts import Qwen3TTSModel

    model = Qwen3TTSModel.from_pretrained(
        "Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign"
    )

    wavs, sr = model.generate_voice_design(
        text="Hello, how can I help you today?",
        language="English",
        instruct="Male, 30 years old, warm and friendly tone, "
                 "professional voice with clear articulation"
    )
    ```
  </Tab>
</Tabs>

### 2. Qwen3-TTS-12Hz-1.7B-CustomVoice

**Best for**: Production applications requiring consistent, high-quality voices

<Tabs>
  <Tab title="Capabilities">
    * 9 premium pre-trained voices
    * Style control via natural language instructions
    * Covers various genders, ages, languages, and dialects
    * Instruction-based emotion and prosody control
    * Streaming generation support
  </Tab>

  <Tab title="Available Voices">
    | Speaker   | Description                           | Native Language           |
    | --------- | ------------------------------------- | ------------------------- |
    | Vivian    | Bright, slightly edgy young female    | Chinese                   |
    | Serena    | Warm, gentle young female             | Chinese                   |
    | Uncle\_Fu | Seasoned male, low mellow timbre      | Chinese                   |
    | Dylan     | Youthful Beijing male, clear natural  | Chinese (Beijing Dialect) |
    | Eric      | Lively Chengdu male, slightly husky   | Chinese (Sichuan Dialect) |
    | Ryan      | Dynamic male, strong rhythmic drive   | English                   |
    | Aiden     | Sunny American male, clear midrange   | English                   |
    | Ono\_Anna | Playful Japanese female, light nimble | Japanese                  |
    | Sohee     | Warm Korean female, rich emotion      | Korean                    |
  </Tab>

  <Tab title="Example">
    ```python theme={null}
    from qwen_tts import Qwen3TTSModel

    model = Qwen3TTSModel.from_pretrained(
        "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice"
    )

    # List available speakers
    print(model.get_supported_speakers())

    wavs, sr = model.generate_custom_voice(
        text="I'm so excited to announce our new product!",
        language="English",
        speaker="Ryan",
        instruct="Very enthusiastic and energetic"
    )
    ```
  </Tab>
</Tabs>

### 3. Qwen3-TTS-12Hz-1.7B-Base

**Best for**: Voice cloning and fine-tuning for custom applications

<Tabs>
  <Tab title="Capabilities">
    * Clone any voice from 3 seconds of audio
    * Maintains speaker characteristics and style
    * Support for reference audio in multiple formats (file, URL, bytes)
    * Can be fine-tuned for specific domains or speakers
    * Streaming generation support
  </Tab>

  <Tab title="Use Cases">
    * Personal voice cloning
    * Voice preservation and restoration
    * Audiobook narration in original voice
    * Custom voice assistants
    * Fine-tuning base for specialized applications
  </Tab>

  <Tab title="Example">
    ```python theme={null}
    from qwen_tts import Qwen3TTSModel

    model = Qwen3TTSModel.from_pretrained(
        "Qwen/Qwen3-TTS-12Hz-1.7B-Base"
    )

    wavs, sr = model.generate_voice_clone(
        text="This is a test of voice cloning.",
        language="English",
        ref_audio="path/to/reference.wav",
        ref_text="The transcript of the reference audio."
    )
    ```
  </Tab>
</Tabs>

### 4. Qwen3-TTS-12Hz-0.6B Models

**Best for**: Applications requiring faster inference or limited resources

The 0.6B variants offer:

* **Faster inference**: \~1.7x faster than 1.7B models
* **Lower memory**: Reduced GPU memory requirements
* **Good quality**: Maintains high quality with slight trade-off vs 1.7B
* **Same features**: CustomVoice and Base variants available

<Note>
  The 0.6B models are ideal for edge devices, high-throughput services, or applications where speed is prioritized over maximum quality.
</Note>

### 5. Qwen3-TTS-Tokenizer-12Hz

**Best for**: Audio compression, transport, and training data preparation

<Tabs>
  <Tab title="Capabilities">
    * Encode audio to discrete codes (compression)
    * Decode codes back to audio (reconstruction)
    * 12Hz frame rate (12 frames per second)
    * 16 residual quantizers
    * 2048 codebook size per quantizer
    * 24kHz sample rate
  </Tab>

  <Tab title="Use Cases">
    * Efficient audio storage and transmission
    * Preparing training data for TTS models
    * Audio codec research
    * Analyzing speech representations
  </Tab>

  <Tab title="Example">
    ```python theme={null}
    from qwen_tts import Qwen3TTSTokenizer

    tokenizer = Qwen3TTSTokenizer.from_pretrained(
        "Qwen/Qwen3-TTS-Tokenizer-12Hz"
    )

    # Encode audio to codes
    codes = tokenizer.encode("input.wav")

    # Decode codes back to audio
    wavs, sr = tokenizer.decode(codes)
    ```
  </Tab>
</Tabs>

## Model Selection Guide

<AccordionGroup>
  <Accordion title="I want to create unique character voices">
    **Recommended**: Qwen3-TTS-12Hz-1.7B-VoiceDesign

    This model excels at generating voices from descriptions. You can specify exact characteristics like "teenage girl with cheerful tone" or "elderly professor with authoritative voice."
  </Accordion>

  <Accordion title="I need consistent professional voices">
    **Recommended**: Qwen3-TTS-12Hz-1.7B-CustomVoice (or 0.6B for faster inference)

    Use the 9 premium pre-trained voices for production applications. They're highly consistent and support instruction-based style control.
  </Accordion>

  <Accordion title="I want to clone a specific person's voice">
    **Recommended**: Qwen3-TTS-12Hz-1.7B-Base (or 0.6B for faster inference)

    Provide 3 seconds of reference audio to clone any voice. Ideal for personal voice assistants or preserving specific speaker characteristics.
  </Accordion>

  <Accordion title="I need fast inference for high-throughput services">
    **Recommended**: Qwen3-TTS-12Hz-0.6B-CustomVoice or 0.6B-Base

    The 0.6B models offer significantly faster inference while maintaining good quality. Perfect for real-time applications or serving many concurrent requests.
  </Accordion>

  <Accordion title="I want to fine-tune for my specific use case">
    **Recommended**: Qwen3-TTS-12Hz-1.7B-Base or 0.6B-Base

    Base models serve as excellent starting points for fine-tuning. See the [Fine-Tuning Guide](/advanced/fine-tuning) for details.
  </Accordion>

  <Accordion title="I need audio compression and codec functionality">
    **Recommended**: Qwen3-TTS-Tokenizer-12Hz

    Use the tokenizer for encode/decode operations, audio compression, or preparing training data.
  </Accordion>
</AccordionGroup>

## Performance Benchmarks

### Content Consistency (WER ↓)

Word Error Rate on Seed-TTS test set:

| Model                    | Chinese  | English  |
| ------------------------ | -------- | -------- |
| Qwen3-TTS-12Hz-1.7B-Base | **0.77** | **1.24** |
| Qwen3-TTS-12Hz-0.6B-Base | 0.92     | 1.32     |
| CosyVoice 3              | **0.71** | 1.45     |
| MiniMax-Speech           | 0.83     | 1.65     |

### Speaker Similarity (Cosine Similarity ↑)

Speaker similarity on multilingual test set:

| Language | 1.7B-Base | 0.6B-Base |
| -------- | --------- | --------- |
| Chinese  | 0.799     | **0.811** |
| English  | 0.775     | **0.829** |
| Japanese | **0.788** | 0.798     |
| Korean   | **0.799** | 0.812     |

<Note>
  **Higher scores** indicate better speaker similarity preservation. The 0.6B model surprisingly outperforms 1.7B in some languages.
</Note>

## Hardware Requirements

### GPU Memory Usage

| Model       | FP16/BF16 | FP32      |
| ----------- | --------- | --------- |
| 1.7B models | \~4-6 GB  | \~8-12 GB |
| 0.6B models | \~2-3 GB  | \~4-6 GB  |
| Tokenizer   | \~1-2 GB  | \~2-4 GB  |

<Warning>
  Memory requirements increase with batch size and sequence length. Add 2-4 GB for FlashAttention 2 and generation overhead.
</Warning>

### Inference Speed

Typical inference times (per second of audio):

| Model | GPU  | Speed (RTF) |
| ----- | ---- | ----------- |
| 1.7B  | A100 | \~0.1x      |
| 1.7B  | V100 | \~0.15x     |
| 0.6B  | A100 | \~0.06x     |
| 0.6B  | V100 | \~0.09x     |

<Info>
  **RTF (Real-Time Factor)**: 0.1x means generating 1 second of audio takes 0.1 seconds. Lower is faster.
</Info>

## Model Downloads

Models are automatically downloaded when you call `from_pretrained()`. For manual downloads:

<Tabs>
  <Tab title="Hugging Face">
    ```bash theme={null}
    pip install -U "huggingface_hub[cli]"

    # Download specific model
    huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign \
      --local-dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign

    huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice \
      --local-dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice

    huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-Base \
      --local-dir ./Qwen3-TTS-12Hz-1.7B-Base

    huggingface-cli download Qwen/Qwen3-TTS-Tokenizer-12Hz \
      --local-dir ./Qwen3-TTS-Tokenizer-12Hz
    ```
  </Tab>

  <Tab title="ModelScope">
    ```bash theme={null}
    pip install -U modelscope

    # Download specific model (recommended for users in Mainland China)
    modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign \
      --local_dir ./Qwen3-TTS-12Hz-1.7B-VoiceDesign

    modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice \
      --local_dir ./Qwen3-TTS-12Hz-1.7B-CustomVoice

    modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-Base \
      --local_dir ./Qwen3-TTS-12Hz-1.7B-Base

    modelscope download --model Qwen/Qwen3-TTS-Tokenizer-12Hz \
      --local_dir ./Qwen3-TTS-Tokenizer-12Hz
    ```
  </Tab>
</Tabs>

## Next Steps

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart/installation">
    Install and start using Qwen3-TTS models
  </Card>

  <Card title="Architecture" icon="diagram-project" href="/concepts/architecture">
    Understand how the models work internally
  </Card>

  <Card title="Language Support" icon="globe" href="/concepts/languages">
    Learn about multilingual capabilities
  </Card>

  <Card title="Fine-Tuning" icon="sliders" href="/guides/fine-tuning">
    Customize models for your specific use case
  </Card>
</CardGroup>