Self-host Speaches with Docker

An OpenAI-compatible speech server: Whisper transcription and text-to-speech behind one API.

This page describes the Levelrail template for Speaches (AI). It deploys the services below as one Docker Compose app on your own server.

Recommended memory: about 2048 MiB.

Services, ports and volumes

Service	Image	Container ports	Volumes
`speaches`	`ghcr.io/speaches-ai/speaches:0.8.3-cpu`	8000	`speaches_models -> /home/ubuntu/.cache/huggingface/hub`

Service	Variable	Value
`speaches`	`ENABLE_UI`	Preset in the template

Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.

In the dashboard, open Apps, choose New app, then Browse templates, and select Speaches. Review the Compose body and deploy.

With the CLI:

levelrail-cli templates deploy speaches --name my-speaches

See Service template catalog for how templates work, and Getting started if you have not installed Levelrail yet.

All templates are listed in the self-host gallery.