SoulX-Podcast

Official inference code for
SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity

SoulX-Podcast_Logo

SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity

Overview

SoulX-Podcast is designed for podcast-style multi-turn, multi-speaker dialogic speech generation, while also achieving superior performance in the conventional monologue TTS task.

To meet the higher naturalness demands of multi-turn spoken dialogue, SoulX-Podcast integrates a range of paralinguistic controls and supports both Mandarin and English, as well as several Chinese dialects, including Sichuanese, Henanese, and Cantonese, enabling more personalized podcast-style speech generation.

Key Features 🔥

Long-form, multi-turn, multi-speaker dialogic speech generation: SoulX-Podcast excels in generating high-quality, natural-sounding dialogic speech for multi-turn, multi-speaker scenarios.
Cross-dialectal, zero-shot voice cloning: SoulX-Podcast supports zero-shot voice cloning across different Chinese dialects, enabling the generation of high-quality, personalized speech in any of the supported dialects.
Paralinguistic controls: SoulX-Podcast supports a variety of paralinguistic events, as as laugher and sighs to enhance the realism of synthesized results.

Install

Clone and Install

Here are instructions for installing on Linux.

Clone the repo

git clone [email protected]:Soul-AILab/SoulX-Podcast.git
cd SoulX-Podcast

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

conda create -n soulxpodcast -y python=3.11
conda activate soulxpodcast
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

pip install -U huggingface_hub

# base model
huggingface-cli download --resume-download Soul-AILab/SoulX-Podcast-1.7B --local-dir pretrained_models/SoulX-Podcast-1.7B

# dialectal model
huggingface-cli download --resume-download Soul-AILab/SoulX-Podcast-1.7B-dialect --local-dir pretrained_models/SoulX-Podcast-1.7B-dialect

Download via python:

from huggingface_hub import snapshot_download

# base model
snapshot_download("Soul-AILab/SoulX-Podcast-1.7B", local_dir="pretrained_models/SoulX-Podcast-1.7B") 

# dialectal model
snapshot_download("Soul-AILab/SoulX-Podcast-1.7B-dialect", local_dir="pretrained_models/SoulX-Podcast-1.7B-dialect")

Download via git clone:

mkdir -p pretrained_models

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

# base model
git clone https://huggingface.co/Soul-AILab/SoulX-Podcast-1.7B pretrained_models/SoulX-Podcast-1.7B

# dialectal model
git clone https://huggingface.co/Soul-AILab/SoulX-Podcast-1.7B-dialect pretrained_models/SoulX-Podcast-1.7B-dialect

Basic Usage

You can simply run the demo with the following commands:

# dialectal inference
bash example/infer_dialogue.sh

TODOs

Add example scripts for monologue TTS.
Publish the technical report.
Develop a WebUI for easy inference.
Deploy an online demo on Hugging Face Spaces.
Dockerize the project with vLLM support.
Add support for streaming inference.

Citation

@misc{SoulXPodcast,
  title        = {SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity},
  author       = {Hanke Xie and Haopeng Lin and Wenxiao Cao and Dake Guo and Wenjie Tian and Jun Wu and Hanlin Wen and Ruixuan Shang and Hongmei Liu and Zhiqi Jiang and Yuepeng Jiang and Wenxi Chen and Ruiqi Yan and Jiale Qian and Yichao Yan and Shunshun Yin and Ming Tao and Xie Chen and Lei Xie and Xinsheng Wang},
  year         = {2025},
  archivePrefix={arXiv},
  url          = {https://arxiv.org/abs/2510.23541}
}

License

We use the Apache 2.0 license. Researchers and developers are free to use the codes and model weights of our SoulX-Podcast. Check the license at LICENSE for more details.

Acknowledge

This repo benefits from FlashCosyVoice

Usage Disclaimer

This project provides a speech synthesis model for podcast generation capable of zero-shot voice cloning, 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.