Model reference · open weights
SoulX-FlashTalk is an open-weight video model from Soul-AILab. SoulX-FlashTalk-14B (BF16) weighs 54.4 GB; the smallest configuration that runs it is L40S 48 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the Soul-AILab/SoulX-FlashTalk-14B model card, 2026-10-01
What it is
| Released by | Soul-AILab |
|---|---|
| Released | 2026-01-08 |
| Parameters | 18.9B |
| VRAM | 54.4 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 5090 32 GB | does not fit | |
| L40S 48 GB | tight (encoders offloaded) | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Le Shen*, Qian Qiao*, Tan Yu*, Ke Zhou, Tianhang Yu, Yu Zhan, Zhenjie Wang, Dingcheng Zhen, Ming Tao, Shunshun Yin, Siyuan Liu ✉
A 4-GPU version of SoulX-FlashTalk and a new open-source real-time streaming digital human model designed specifically for consumer-grade GPUs like 4090 etc.
conda create -n flashtalk python=3.10
conda activate flashtalk
pip install torch==2.7.1 torchvision==0.22.1 --index-url https://download.pytorch.org/whl/cu128
pip install -r requirements.txt
pip install ninja
pip install flash_attn==2.8.0.post2 --no-build-isolation
# Ubuntu / Debian
apt-get install ffmpeg
# CentOS / RHEL
yum install ffmpeg ffmpeg-devel
or
# Conda (no root required)
conda install -c conda-forge ffmpeg==7
| Model Component | Description | Link |
|---|---|---|
SoulX-FlashTalk-14B | Our 14b model | 🤗 Huggingface |
chinese-wav2vec2-base | chinese-wav2vec2-base | 🤗 Huggingface |
# If you are in china mainland, run this first: export HF_ENDPOINT=https://hf-mirror.com
pip install "huggingface_hub[cli]"
huggingface-cli download Soul-AILab/SoulX-FlashTalk-14B --local-dir ./models/SoulX-FlashTalk-14B
huggingface-cli download TencentGameMate/chinese-wav2vec2-base --local-dir ./models/chinese-wav2vec2-base
# Infer on single GPU
# Requires more than 64G of VRAM
bash inference_script_single_gpu.sh
# Infer on multy GPUs
# Real-time inference speed can only be supported on 8xH800 or higher graphics cards
bash inference_script_multi_gpu.sh
Coming Soon!
If you are interested in leaving a message to our work, feel free to email le.shen@mail.dhu.edu.cn or qiaoqian@soulapp.cn or yutan@soulapp.cn or zhouke@soulapp.cn or liusiyuan@soulapp.cn
You’re welcome to join our WeChat group for technical discussions, updates.
If you find our work useful in your research, please consider citing:
@misc{shen2025soulxflashtalktechnicalreport,
title={SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation},
author={Le Shen and Qian Qiao and Tan Yu and Ke Zhou and Tianhang Yu and Yu Zhan and Zhenjie Wang and Ming Tao and Shunshun Yin and Siyuan Liu},
year={2025},
eprint={2512.23379},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2512.23379},
}
[!TIP] If you find our work useful, please also consider starring the original repositories of these foundational methods.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel and load the workflow from the model's card on Hugging Face; choose this model's file in its loader.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (7.3 GB)
get Soul-AILab/SoulX-FlashTalk-14B diffusion_pytorch_model-00004-of-00004.safetensors diffusion_models
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT