About OMU TTS

What is OMU TTS?

OMU TTS is a text-to-speech web application: you enter text, choose a language and voice, and download a WAV file. OMU means parrot in Japanese — a nod to voices that repeat your words clearly.

Speech is powered by the Kokoro-82M model, served through a dedicated TTS API (OMU IA TTS). This site is the public-facing studio that talks to that API securely.

Project context

OMU TTS is an individual project — not a group assignment. I work on it alone as a solopreneur: one person covering product, design, frontend, and integration with the backend API.

Who is behind it?

Ahiru-T3ch is me — my solo studio name for shipping software. When you see “by Ahiru-T3ch” in the footer, that is the same person who designs, builds, and maintains OMU TTS. There is no separate team hidden behind the brand for this product.

Questions, partnerships, or early access: reach out via ahiru-t3ch.com.

Skills & stack

This project showcases full-stack delivery: a modern web UI, server-side API routes that proxy the TTS backend (token never exposed to the browser), and containerized deployment.

• Next.js & React
• TypeScript
• Tailwind CSS
• REST API integration
• Docker & Compose
• UI / UX design
• TTS pipelines (Kokoro)

Frontend: Next.js, React, TypeScript, Tailwind CSS · Backend bridge: Next.js Route Handlers · TTS service: OMU IA TTS (Docker) · Infra: Docker Compose, environment-based configuration.

Roadmap