---
license: mit
base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
tags:
- text-to-speech
- tts
- speech
- audio
- qwen
- qwen3
- qwen-tts
- neural-tts
- single-speaker
- voice
- character-voice
- celune
pipeline_tag: text-to-speech
language:
- en
- zh
- ja
- ko
- fr
- de
- es
- it
- pt
- ru
library_name: faster-qwen3-tts
datasets:
- lunahr/CeluneData-Energetic
---

# Celune - Energetic

“It’s not just a TTS, it’s a character.”

Celune is a single-speaker neural TTS voice built on top of Qwen3-TTS.
This model defines one identity, one voice, and one consistent speaking style.


## Overview
- Model: Qwen3-TTS-12Hz-1.7B-Base (finetuned)
- Type: Single-speaker voice
- Language: English + 9 others
- Style: High energy, expressive delivery

This is part of the Celune voice lineup, where each model represents a distinct interpretation of the same character.


## Voice Description

A high-energy voice with strong expressiveness and a wider dynamic range, suited for emphasis and excitement.


Characteristics
- Consistent timbre across generations
- Expanded expressiveness beyond reference audio
- Supports prompt-based tone steering
- Stable pacing and pronunciation
- Designed for real-time or near real-time usage


## Usage

### Basic Example

```py
import numpy as np
import soundfile as sf
from faster_qwen3_tts import FasterQwen3TTS

model = FasterQwen3TTS.from_pretrained("lunahr/Celune-1.7B-Energetic")

buffer = []
for audio_chunk, sr, timing in model.generate_custom_voice_streaming(
    text="Hello, this is Celune.",
    language="Auto",
    speaker="celune"
):
    buffer.append(audio_chunk)

wav = np.concatenate(buffer)
sf.write("output.wav", wav, 24000)
```

### Sample Output

<audio controls>
  <source src="https://huggingface.co/lunahr/Celune-1.7B-Energetic/resolve/main/sample.wav?download=true" type="audio/wav">
</audio>


## Prompt Steering

You can influence delivery style using text or instruct prompts:

Examples:
- “whisper this softly”
- “speak with excitement”
- “calm and slow delivery”

The model will stay within the defined voice but expand expression.


## Notes
- This is a single-speaker model. It does not support multiple voices.
- Voice identity is fixed and defined by training data.
- Avoid mixing languages mid-sentence for best stability.
- Avoid special tokens or markup in spoken text.


## Intended Use
- Character voices
- Assistive TTS
- Offline voice systems
- Creative projects and prototyping


## Limitations
- Not designed for multi-speaker tasks
- Extreme prompts may introduce instability
- Long mixed-language inputs may degrade output


## About Celune

Celune is a local-first TTS system focused on speed, control, and identity.

Each model in the Celune lineup is:
- self-contained
- stylistically distinct
- built around the same core character concept


## License

MIT and [Qwen's Apache 2.0 license](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)


## Credits
- Base model: Qwen3-TTS-12Hz-1.7B-Base
- Finetuning + voice design: https://huggingface.co/lunahr