Build From Source#

This page covers building the Text To Speech microservice from source for both Docker and standalone host execution.

Prerequisites#

  • Verify the System Requirements.

  • Clone the repository and cd into the text-to-speech/ directory.

Build the Docker Image#

The repository ships a Dockerfile and a docker-compose.yml. To build the image as part of the Compose stack:

docker compose build
docker compose up -d

To build the image directly with docker:

docker build -t text-to-speech:local .

The Compose setup mounts config.yaml, models/, storage/, and the Hugging Face cache into the container, and passes /dev/dri through for host Intel iGPU access by default. The container runs as UID/GID 1000:1000 by default; see Troubleshooting if your host user differs.

Build a Python Environment (Standalone)#

Install host packages, then create a virtual environment and install Python dependencies from source:

sudo apt-get update
sudo apt-get install -y libsndfile1

python -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txt
python main.py

Verifying the Build#

After building and starting the service, confirm:

curl --noproxy '*' http://127.0.0.1:8011/health

A {"status": "ok"} response confirms the build is functional.