Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/SparkAudio/Spark-TTS

Spark-TTS Inference Code
https://github.com/SparkAudio/Spark-TTS

Last synced: 8 months ago
JSON representation

Spark-TTS Inference Code

Awesome Lists containing this project

README 

          


    


    Spark-TTS

    


    


    Official PyTorch code for inference of 


    Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

    


    


    Spark-TTS Logo

    


        


        Institution 1

        Institution 2

        Institution 3

    


    


        Institution 4

        Institution 5

        Institution 6

    


    


    


    paper

    version

    Hugging Face

    version

    version

    python

    mit




## Spark-TTS 🔥



### Overview



Spark-TTS is an advanced text-to-speech system that uses the power of large language models (LLM) for highly accurate and natural-sounding voice synthesis. It is designed to be efficient, flexible, and powerful for both research and production use.



### Key Features



- **Simplicity and Efficiency**: Built entirely on Qwen2.5, Spark-TTS eliminates the need for additional generation models like flow matching. Instead of relying on separate models to generate acoustic features, it directly reconstructs audio from the code predicted by the LLM. This approach streamlines the process, improving efficiency and reducing complexity.

- **High-Quality Voice Cloning**: Supports zero-shot voice cloning, which means it can replicate a speaker's voice even without specific training data for that voice. This is ideal for cross-lingual and code-switching scenarios, allowing for seamless transitions between languages and voices without requiring separate training for each one.

- **Bilingual Support**: Supports both Chinese and English, and is capable of zero-shot voice cloning for cross-lingual and code-switching scenarios, enabling the model to synthesize speech in multiple languages with high naturalness and accuracy.

- **Controllable Speech Generation**: Supports creating virtual speakers by adjusting parameters such as gender, pitch, and speaking rate.



---



  

    Inference Overview of Voice Cloning


  

  

    Inference Overview of Controlled Generation


  



## 🚀 News



- **[2025-03-04]** Our paper on this project has been published! You can read it here: [Spark-TTS](https://arxiv.org/pdf/2503.01710). 



## Install

**Clone and Install**



  Here are instructions for installing on Linux. If you're on Windows, please refer to the [Windows Installation Guide](https://github.com/SparkAudio/Spark-TTS/issues/5).  

*(Thanks to [@AcTePuKc](https://github.com/AcTePuKc) for the detailed Windows instructions!)*



- Clone the repo

``` sh

git clone https://github.com/SparkAudio/Spark-TTS.git

cd Spark-TTS

```



- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html

- Create Conda env:



``` sh

conda create -n sparktts -y python=3.12

conda activate sparktts

pip install -r requirements.txt

# If you are in mainland China, you can set the mirror as follows:

pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com

```



**Model Download**



Download via python:

```python

from huggingface_hub import snapshot_download



snapshot_download("SparkAudio/Spark-TTS-0.5B", local_dir="pretrained_models/Spark-TTS-0.5B")

```



Download via git clone:

```sh

mkdir -p pretrained_models



# Make sure you have git-lfs installed (https://git-lfs.com)

git lfs install



git clone https://huggingface.co/SparkAudio/Spark-TTS-0.5B pretrained_models/Spark-TTS-0.5B

```



**Basic Usage**



You can simply run the demo with the following commands:

``` sh

cd example

bash infer.sh

```



Alternatively, you can directly execute the following command in the command line to perform inference：



``` sh

python -m cli.inference \

    --text "text to synthesis." \

    --device 0 \

    --save_dir "path/to/save/audio" \

    --model_dir pretrained_models/Spark-TTS-0.5B \

    --prompt_text "transcript of the prompt audio" \

    --prompt_speech_path "path/to/prompt_audio"

```



**Web UI Usage**



You can start the UI interface by running `python webui.py --device 0`, which allows you to perform Voice Cloning and Voice Creation. Voice Cloning supports uploading reference audio or directly recording the audio.



| **Voice Cloning** | **Voice Creation** |

|:-------------------:|:-------------------:|

| ![Image 1](src/figures/gradio_TTS.png) | ![Image 2](src/figures/gradio_control.png) |



**Optional Methods**



For additional CLI and Web UI methods, including alternative implementations and extended functionalities, you can refer to:



- [CLI and UI by AcTePuKc](https://github.com/SparkAudio/Spark-TTS/issues/10)



## **Demos**



Here are some demos generated by Spark-TTS using zero-shot voice cloning. For more demos, visit our [demo page](https://sparkaudio.github.io/spark-tts/).



---



    

**Donald Trump**



    

**Zhongli (Genshin Impact)**



[Donald Trump](https://github.com/user-attachments/assets/fb225780-d9fe-44b2-9b2e-54390cb3d8fd)



    

[Zhongli](https://github.com/user-attachments/assets/80eeb9c7-0443-4758-a1ce-55ac59e64bd6)



---



    

**陈鲁豫 Chen Luyu**



    

**杨澜 Yang Lan**



    

[陈鲁豫Chen_Luyu.webm](https://github.com/user-attachments/assets/5c6585ae-830d-47b1-992d-ee3691f48cf4)



    

[Yang_Lan.webm](https://github.com/user-attachments/assets/2fb3d00c-abc3-410e-932f-46ba204fb1d7)



---



    

**余承东 Richard Yu**



    

**马云 Jack Ma**



[Yu_Chengdong.webm](https://github.com/user-attachments/assets/78feca02-84bb-4d3a-a770-0cfd02f1a8da)



    

[Ma_Yun.webm](https://github.com/user-attachments/assets/2d54e2eb-cec4-4c2f-8c84-8fe587da321b)



---



    

**刘德华 Andy Lau**



**徐志胜 Xu Zhisheng**



[Liu_Dehua.webm](https://github.com/user-attachments/assets/195b5e97-1fee-4955-b954-6d10fa04f1d7)



    

[Xu_Zhisheng.webm](https://github.com/user-attachments/assets/dd812af9-76bd-4e26-9988-9cdb9ccbb87b)



---



    

**哪吒 Nezha**



    

**李靖 Li Jing**



[Ne_Zha.webm](https://github.com/user-attachments/assets/8c608037-a17a-46d4-8588-4db34b49ed1d)



[Li_Jing.webm](https://github.com/user-attachments/assets/aa8ba091-097c-4156-b4e3-6445da5ea101)



## To-Do List



- [x] Release the Spark-TTS paper.

- [ ] Release the training code.

- [ ] Release the training dataset, VoxBox.



## Citation



```

@misc{wang2025sparktts,

      title={Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens}, 

      author={Xinsheng Wang and Mingqi Jiang and Ziyang Ma and Ziyu Zhang and Songxiang Liu and Linqin Li and Zheng Liang and Qixi Zheng and Rui Wang and Xiaoqin Feng and Weizhen Bian and Zhen Ye and Sitong Cheng and Ruibin Yuan and Zhixian Zhao and Xinfa Zhu and Jiahao Pan and Liumeng Xue and Pengcheng Zhu and Yunlin Chen and Zhifei Li and Xie Chen and Lei Xie and Yike Guo and Wei Xue},

      year={2025},

      eprint={2503.01710},

      archivePrefix={arXiv},

      primaryClass={cs.SD},

      url={https://arxiv.org/abs/2503.01710}, 

}

```



## ⚠️ Usage Disclaimer



This project provides a zero-shot voice cloning TTS model intended for academic research, educational purposes, and legitimate applications, such as personalized speech synthesis, assistive technologies, and linguistic research.



Please note:



- Do not use this model for unauthorized voice cloning, impersonation, fraud, scams, deepfakes, or any illegal activities.



- Ensure compliance with local laws and regulations when using this model and uphold ethical standards.



- The developers assume no liability for any misuse of this model.



We advocate for the responsible development and use of AI and encourage the community to uphold safety and ethical principles in AI research and applications. If you have any concerns regarding ethics or misuse, please contact us.