# Get Started

This page is the entry point for running the Text To Speech microservice.
Pick one of the two deployment paths and follow the linked guide.

## Before You Begin

- Confirm that your machine meets the
  [System Requirements](./get-started/system-requirements.md).
- Review the [Configuration Guide](./get-started/configuration.md) if you plan to change
  models, runtimes, devices, or precision.

## Choose Deployment Path

::::{tab-set}
:::{tab-item} Run in Docker (Recommended)
:sync: Docker 

The container image exposes the API on host port `8011` and mounts shared
folders for models, storage, and the Hugging Face cache.

See [Run with Docker Compose](./get-started/run-container.md) for the full step-by-step guide.

Quick start:

```bash
docker compose up -d --build
curl --noproxy '*' http://127.0.0.1:8011/health
```

If you hit permission errors on `models/`, `storage/`, or
`.cache/huggingface/`, see
[Troubleshooting](./troubleshooting.md#permission-errors-on-mounted-folders).

:::
:::{tab-item} Run on the Host
:sync: Host 

Run the service directly with Python. This path is useful for development or
when you do not want to use Docker.

See [Run on the Host](./get-started/run-standalone.md) for the full step-by-step guide.

Quick start:

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

:::
::::

## Verify

Once the service is running:

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

Expected response:

```json
{"status": "ok"}
```

## Next Steps

- [API Reference](./api-reference.md) for endpoint details and examples
- [Configuration Guide](./get-started/configuration.md) to customize the model, runtime, and
  device
- [Troubleshooting](./troubleshooting.md) for common startup issues


:::{toctree}
:hidden:

./get-started/system-requirements.md
./get-started/configuration.md
./get-started/build-from-source.md
./get-started/run-container.md
./get-started/run-standalone.md

:::