Official Demo From F5-TTS

Official one:

For Hindi:

Demo.mp4

Local Set Up

Step 1: Create and activate a virtual environment

Using virtualenv

Create a virtual environment

python -m venv f5-tts

Activate the virtual environment (Linux/Mac)

source f5-tts/bin/activate

Activate the virtual environment (Windows)

f5-tts\Scripts\activate

Using conda

Create a python 3.10 conda env (you could also use virtualenv)

conda create -n f5-tts python=3.10
conda activate f5-tts

Step 2: Check CUDA version (if needed)

nvcc --version

Step 3: Install PyTorch and Torchaudio with CUDA pytorch.org

pip install torch==2.3.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118
pip install torchaudio==2.3.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118

Step 4: Install other dependencies

pip install git+https://github.com/SWivid/F5-TTS.git

Step 6: Run the application

Launch a Gradio app (web interface)

f5-tts_infer-gradio

Specify the port/host

f5-tts_infer-gradio --port 7860 --host 0.0.0.0

Launch a share link

f5-tts_infer-gradio --share

Step 7: Deactivate the virtual environment when done

deactivate

Unofficial F5-TTS-Demo

1. Run on Google Colab Cell

2. Run Using Gradio App

3. SRT to Audio Generation (Subtitle Dubbing)

F5-TTS Video Dubbing from Any Languages to English or Chinese (Only Single Speaker Supported)

Follow this Colab Notebook to run it on local device too

Credit

F5-TTS

@article{chen-etal-2024-f5tts,
      title={F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching}, 
      author={Yushen Chen and Zhikang Niu and Ziyang Ma and Keqi Deng and Chunhui Wang and Jian Zhao and Kai Yu and Xie Chen},
      journal={arXiv preprint arXiv:2410.06885},
      year={2024},
}