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

Mimi

Mimi is a desktop application that captures system or microphone audio and displays live translated subtitles in a floating window. It can show original text, translation or bilingual captions, and optionally save subtitle or audio files locally.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mimi — 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 Mimi while listening to spoken content when you want translated or bilingual captions displayed over the screen, and can configure an appropriate speech and translation service or supported Apple-native option.

Who it is for

  • People following online classes or meetings in another language.
  • Viewers who want translated captions over films or livestreams.
  • Language learners who benefit from seeing original and translated speech together.

Documented uses

  • Turn computer or microphone speech into live translated captions.
  • Choose between original, translated and bilingual subtitle display.
  • Adjust an on-screen caption overlay and optionally export subtitles as TXT or audio as WAV.
Before you choose

Requirements & limits

The README lists desktop support for macOS 13 or later, Windows x64 and Linux x86_64, and also references an Android app. Mimi is open source under the MIT license.

  • Cloud-based recognition requires provider credentials, sends audio to that service and may incur charges.
  • Apple Speech recognition and Apple Translate have separate requirements and are documented for qualifying Apple silicon Macs on macOS 26 or later.
  • System-audio permissions differ by macOS version; macOS 14.2 and later can use system-audio-only permission, while earlier versions require screen-recording and system-audio permission.
  • Recording and saving are off by default; TXT subtitle and WAV audio export are optional.

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

Configure Mimi for live translated captions

Set up a provider, choose languages and start captions for playing audio.

Before you start

  • Mimi on a supported desktop platform.
  • Credentials for a cloud speech or translation provider, unless using the documented qualifying Apple-native options.
  • Required audio-capture permissions for the macOS version in use.

Steps

  1. In Settings → Speech and Translation, add a configuration and enter provider credentials as prompted; save it.

  2. Choose the recognition and translation languages.

  3. Play the audio, open the Subtitles page and enable Live Subtitles.

Expected outcome

Mimi displays captions for the selected computer or microphone audio, in the configured original, translated or bilingual mode.

Guide limitations

  • Cloud recognition sends audio to the selected provider and may incur charges.
  • Apple Speech local recognition requires Apple silicon, macOS 26 or later, and an available system recognition engine.
  • On macOS before 14.2, system-audio capture requires Screen Recording and System Audio permission.
Documentation 1 ↗
Evidence and transparency

Sources & review

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