vui

What it does

A single Python server that transcribes your speech, runs a local LLM and streams a TTS reply — built on Vui Nano, a 300M speech transformer trained on conversational audio complete with breaths, laughter and hesitations. A hosted demo was up on 2026-08-18. This is the open core: newer models and the better turn-taking live in the vendor's paid API, so calibrate expectations against that rather than against a product. Apache-2.0, confirmed in the licence text.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

• Setup difficultySome setup needed
• Command lineRequired
• API keyNot required
• Sends data onlineYes

Judged automatically from the project's own metadata. Always confirm on the official page.

vui FAQ

Is vui free?

The source is open, but the build distributed through the app store may be a paid download. Check the store listing before installing.

Do I need to install anything or write code to use vui?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does vui work on a phone?

No. It needs a computer.

Can I use vui commercially?

The project does not state a clear licence, so commercial use cannot be confirmed here. Check the official page or ask the author before using it at work.

How it compares

The conditions that decide whether you can actually use it, side by side.

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other ai agents tools