Kokoro-FastAPI on Ubuntu 24.04

Azure Artificial Intelligence (AI)

a self hosted, OpenAI compatible text to speech server wrapping the compact Kokoro speech model, secured from first boot by cloudimg.

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

Kokoro-FastAPI is an open source, self hosted text to speech server. It wraps the compact Kokoro 82M speech model behind an OpenAI compatible HTTP API, so any client that already speaks the OpenAI audio format can generate natural speech from text against your own endpoint. It ships with dozens of built in voices across several languages, voice mixing, adjustable speed, optional word level timestamps, streaming, and a range of audio output formats.

It suits developers and teams who want to add speech to their applications without sending text to a third party service or paying per character cloud bills, and who prefer to own the whole pipeline inside their own cloud account.

Why the cloudimg image

cloudimg ships Kokoro-FastAPI behind an nginx reverse proxy that enforces an OpenAI style Bearer token on every request except the health check, so the speech endpoint is never open to the internet. A fresh, unique API key is generated on the first boot of every instance, with no default or shared key surviving into the image, and the application binds to the loopback interface so it never listens on a public interface directly. The speech model and every built in voice are baked into the image so it synthesizes speech offline the moment it boots, with no model download. No GPU is required. Every deployment is paired with a step by step guide and backed by 24/7 cloudimg support.

Common uses

  • Add natural text to speech to your apps against an endpoint you own
  • A drop in, self hosted alternative to a metered cloud speech API
  • Batch narration and voiceover generation with dozens of built in voices