> ## 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.

# Tokenizer API Overview

> Encode and decode audio using Qwen3-TTS speech tokenizers

The Tokenizer API provides a unified interface for encoding audio into discrete codes and decoding them back to waveforms. It supports both 25Hz and 12Hz tokenizer models.

## Qwen3TTSTokenizer Class

The `Qwen3TTSTokenizer` class is a wrapper for Qwen3 TTS Tokenizers with HuggingFace-style loading and inference. It provides:

* **HuggingFace Integration**: Load models using `from_pretrained()`
* **Flexible Input Formats**: Support for file paths, URLs, base64 strings, and numpy arrays
* **Batch Processing**: Encode and decode multiple audio files simultaneously
* **Automatic Resampling**: Handles sample rate conversion automatically

<Note>
  Defined in `qwen_tts/inference/qwen3_tts_tokenizer.py:44`
</Note>

## Key Features

### Supported Input Formats

The tokenizer accepts audio in multiple formats:

* **File paths**: Local WAV files
* **URLs**: HTTP/HTTPS audio URLs
* **Base64 strings**: Encoded audio data (with or without data URL prefix)
* **NumPy arrays**: Raw waveform arrays (requires `sr` parameter)
* **Batch inputs**: Lists of any of the above formats

### Model Variants

* **25Hz Tokenizer** (`Qwen/Qwen3-TTS-Tokenizer-25Hz`): Returns audio codes, x-vectors, and reference mel-spectrograms
* **12Hz Tokenizer** (`Qwen/Qwen3-TTS-Tokenizer-12Hz`): Returns multi-quantizer audio codes

### Return Types

<Tip>
  For numpy array input, you **must** pass the `sr` parameter to specify the original sampling rate.
</Tip>

## Quick Navigation

<CardGroup cols={2}>
  <Card title="Qwen3TTSTokenizer" icon="microchip" href="/api/tokenizer/qwen3tts-tokenizer">
    Class initialization and loading methods
  </Card>

  <Card title="Encode & Decode" icon="arrow-right-arrow-left" href="/api/tokenizer/encode-decode">
    Encoding audio to codes and decoding back to waveforms
  </Card>
</CardGroup>

## Basic Usage

```python theme={null}
from qwen_tts import Qwen3TTSTokenizer

# Load tokenizer
tokenizer = Qwen3TTSTokenizer.from_pretrained(
    "Qwen/Qwen3-TTS-Tokenizer-12Hz",
    device_map="cuda:0"
)

# Encode audio
encoded = tokenizer.encode("audio.wav")

# Decode back to waveform
wavs, sample_rate = tokenizer.decode(encoded)
```