ToSpeech

ToSpeech is a local web application for audio generation, featuring a React frontend and a FastAPI backend with Celery/Valkey for asynchronous task processing.

• Python Environment (Choose one):
  • Conda (Anaconda or Miniconda)
  • Python 3.9+ (Standard installation)
• Node.js 18+
• Valkey (Redis alternative)
  • macOS: brew install valkey
  • Windows: Memurai or WSL
  • Linux: sudo apt install valkey

Navigate to the Backend directory and choose your preferred environment manager.

cd Backend
conda create -n tospeech python=3.10
conda activate tospeech
pip install -r requirements.txt

cd Backend
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

Navigate to the Frontend directory and install dependencies.

cd ../Frontend
npm install

You will need 4 terminal windows to run the full stack locally.

Start the Valkey server on port 1312.

cd Backend
./start_valkey.sh

Start the background worker. Ensure your environment is activated.

Conda:

cd Backend
conda activate tospeech
./start_celery.sh

venv:

cd Backend
source venv/bin/activate
./start_celery.sh

Start the FastAPI server on port 1311. Ensure your environment is activated.

Conda:

cd Backend
conda activate tospeech
uvicorn main:app --reload --port 1311

venv:

cd Backend
source venv/bin/activate
uvicorn main:app --reload --port 1311

Start the React development server.

cd Frontend
npm run dev

The application will be available at http://localhost:1310.

• Frontend: http://localhost:1310 (Vite)
• Backend API: http://localhost:1311 (FastAPI)
• Valkey: localhost:1312 (Broker)

This project utilizes code from VibeVoice by Microsoft (and its community fork), which is licensed under the MIT License. We gratefully acknowledge their open-source contribution.

The VibeVoice code is located in Backend/VibeVoice1.5/ and retains its original MIT license. Please refer to Backend/VibeVoice1.5/LICENSE for full terms regarding that component.

ToSpeech's original code is licensed under the GNU General Public License v3.0 (GPLv3). See the main LICENSE file for details.