OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Aiui

Aiui is a Python-based, MIT-licensed browser interface for spoken conversations with AI models. It captures voice input, sends it to a configured model, and returns a synthesized speech response; its documentation describes GPT-3.5 and GPT-4 support and desktop and mobile browser use.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Aiui — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Aiui when spoken input and synthesized replies suit a conversational AI interaction, or when you want to build a local browser-based voice interface around a configured model.

Who it is for

  • People who want to converse with an AI model by speaking and listening in a browser.
  • Developers who want to build and run a Docker-based voice interface locally.
  • Teams exploring a voice-enabled kiosk or hands-free information interface.

Documented uses

  • Speak a prompt instead of typing it and hear the model's response aloud.
  • Configure the completion model, text-to-speech provider, voice, and language for a local instance.
Before you choose

Requirements & limits

The README documents desktop and mobile browser use and a local Docker setup. The local setup example requires an OpenAI API key.

  • The documented model choices are GPT-3.5 and GPT-4; GPT-4 requires API-key access.
  • The local Docker example selects edge_tts and an English voice.
  • Non-English language settings are supported only with gTTS or edge_tts text-to-speech providers.
  • The project describes open-model support as under development.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build and start Aiui locally with Docker

Build the documented Docker image and start a local browser-accessible Aiui instance.

Before you start

  • Git and Docker
  • An OpenAI API key with access to the selected model
  • A modern browser

Steps

  1. Clone the AIUI repository and change into its directory.

  2. Build the image with the command below; for ARM64, the README gives the command below.

    Documented command
    docker build -t aiui .
    Documented command
    docker buildx build --platform linux/arm64 -t aiui .

  3. Create a container using the documented environment settings: OPENAI_API_KEY, TTS_PROVIDER=EDGETTS, and EDGETTS_VOICE=en-US-EricNeural, mapping port 8000 to port 80.

  4. Open localhost:8000 in a modern browser.

Expected outcome

A locally served Aiui interface for spoken conversations with the configured AI model.

Guide limitations

  • The README's Docker example uses an OpenAI API key.
  • GPT-4 requires an API key with access to that model.
  • Languages other than English are supported only with gTTS or edge_tts text-to-speech providers.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
lspahija/AIUI · Official homepage title · retained in its source language
How we review sourcesSuggest a correction