Piper TTS on Ubuntu 24.04 LTS

Azure Artificial Intelligence (AI)

Turn text into natural sounding speech privately on your own machine, on CPU alone, behind one authenticated API.

Base

Hardened build

minimal ports, security patches applied at build time

Access

Unique credentials

generated on first boot, readable only by root

Verified

Boots working

services pass a health gate before release

Support

24/7, 365 days

by email and live chat, 24 hour response SLA

Overview

Piper is an open source neural text to speech system that synthesises natural sounding speech locally, using ONNX Runtime on the CPU with no GPU and no external speech service. You send it text over a small HTTP API or type it into a browser interface, and it returns WAV audio. Because synthesis happens on the machine you control, the text never leaves your network, which matters when it is customer records, clinical notes or anything else you cannot hand to a hosted service.

It suits adding speech to an application, producing audio for accessibility, narrating documents and alerts, and giving a self hosted assistant a voice.

Why the cloudimg image

Piper ships with no authentication and would otherwise publish an open synthesis endpoint on a public address, so cloudimg binds the Piper server to loopback and fronts it with an nginx TLS proxy that enforces HTTP Basic auth. A fresh password and TLS certificate are generated on the first boot of every instance and written to a root only file, so no two instances share a login and no default credential ever ships. The endpoint that makes the server fetch voice files from the internet is disabled. A voice model is included and ready to speak immediately: cloudimg screened its licence to the root of its training lineage and ships only a public domain voice cleared for commercial use, with the licence position for both the engine and the voice recorded on the instance. The base is fully patched, every deployment is paired with a step by step deploy guide, and it is backed by 24/7 cloudimg support.

Common uses

Add a private speech voice to an application or assistant
Generate spoken audio for accessibility and narration
Synthesise speech on infrastructure you control, with no external speech API

See it running

Real screenshots taken while testing this image against its deployment guide.

Piper TTS on Ubuntu 24.04 LTS screenshot 1

Piper TTS on Ubuntu 24.04 LTS screenshot 2

Piper TTS on Ubuntu 24.04 LTS screenshot 3

Piper TTS on Ubuntu 24.04 LTS screenshot 4

Overview

Why the cloudimg image

Common uses

See it running

More in Artificial Intelligence (AI)

AnythingLLM

Infinity Embeddings Server

Label Studio

LibreChat AI Chat Platform - with

LiteLLM

LocalAI