# Self-host Wyoming Piper

> Fast local text to speech over the Wyoming protocol, used by Home Assistant voice assistants. Downloads the chosen voice on first start.

- Page: https://levelrail.com/templates/wyoming-piper/
- JSON: https://levelrail.com/templates/wyoming-piper.json
- Category: AI
- Licence: MIT (Permissive license)
- Source: https://github.com/rhasspy/wyoming-piper
- Upstream docs: https://github.com/rhasspy/wyoming-piper#readme

## Requirements
- Memory: about 512 MiB
- amd64: unknown, arm64: unknown
- Needs configuration before start: no
- Pinned image tag: 2.5.2

## Services

| Service | Image | Tag | Ports | Volumes |
| --- | --- | --- | --- | --- |
| wyoming-piper | rhasspy/wyoming-piper | 2.5.2 | 10200 | data -> /data |

## Deploy

### CLI

```bash
levelrail-cli templates deploy wyoming-piper --name my-wyoming-piper
```

### API

```bash
curl -X POST -H "Authorization: Bearer $TOKEN" \
  https://levelrail.example.com/api/v1/service-templates/wyoming-piper/deploy
```

Create a token in the dashboard first. This one-click route deploys it as a trial app you can keep or remove.

## First run
1. Add the Wyoming integration in Home Assistant and point it at port 10200. The first start downloads the voice, so wait a minute.

## Questions

### Can I deploy Wyoming Piper on Dokploy or Dokku?

The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list we compared does not have an entry with the same id for Wyoming Piper, so on Dokploy you would use a Docker Compose application with the file from this page. Dokku deploys container images with its own commands, so the pinned image rhasspy/wyoming-piper:2.5.2 is what you deploy there.

Self-host Wyoming Piper, Wyoming Piper docker compose file, deploy Wyoming Piper on a VPS: this page lists the pinned image, ports, volumes and the commands for each.
