Live Translator for MAC
Free, open-source menu bar app that translates any audio playing on your Mac live on screen, using your own OpenAI or Google Gemini API key.
Live Translator Overview
Live Translator is a free, open-source Mac app that translates whatever audio your Mac is playing, such as YouTube videos, podcasts, meetings and movies, and shows the translation live in a floating panel. It sits in the menu bar, captures system audio through Apple's ScreenCaptureKit, turns the speech into text and sends the text to an AI model that writes a natural translation. The AI sees the whole conversation, so the translation reads like a growing document rather than word-by-word subtitles, and new parts are highlighted.
Live Translator is made by Umut Çetinkaya and released under the MIT licence. Version 0.1.0 added a choice of AI provider: you enter your own OpenAI or Google Gemini API key in Settings, and the app uses that provider for translation. Speech recognition runs on the Mac by default, so your audio does not leave it; an optional realtime mode streams audio to OpenAI for lower latency instead. The app needs macOS 13 or later and the Screen & System Audio Recording permission. It is an early 0.1 release, and macOS may block the first launch: right-click the app and choose Open, or clear the quarantine flag in Terminal.
Key Features
Live Translator turns any audio on your Mac into a live translation you can read.
- System audio capture: translates audio from any app, with no audio driver to install.
- Many languages: 11 spoken source languages and 12 target languages.
- Context-aware translation: the AI keeps the whole conversation in view.
- On-device speech recognition: the default mode keeps your audio on the Mac.
- Optional realtime mode: lower latency through OpenAI's realtime translation model.
- Text-to-speech: hear translations with the offline Piper voice or OpenAI and Gemini voices.
- Floating overlay: a dark, draggable panel that stays on top of other windows.
- Menu bar controls: pause, show or hide the panel and quit from the menu bar.
What’s New in Version 0.1.0
Live Translator 0.1.0 adds multiple AI providers and an optional realtime mode.
- Choose OpenAI or Google Gemini for translation and switch any time in Settings
- Refreshed list of the latest OpenAI and Gemini models
- Optional realtime mode through OpenAI's Realtime Translation model, with a privacy warning
- Audio sources opened after the app starts are now captured automatically
- Redesigned Settings with grouped sections and fields for each provider
- Clearer messages when a provider, key or connection fails, and a hint when no audio is detected
Live Translator FAQ
Is Live Translator free?
Yes. Live Translator is free and open source under the MIT licence. Translation runs through your own OpenAI or Google Gemini API key, so any charges for using that provider are between you and the provider.
What does Live Translator do?
It captures the audio your Mac is playing, such as a YouTube video, a podcast or a meeting, recognizes the speech and shows a live translation in a floating panel on screen.
Which macOS version does Live Translator need?
Live Translator needs macOS 13 Ventura or later. It uses ScreenCaptureKit to capture system audio, so no extra audio driver is needed.
Do I need an API key?
Yes. After launching the app, open Settings, pick OpenAI or Google Gemini as the provider and enter your API key for it.
Does my audio leave my Mac?
Not in the default mode: speech recognition runs on the Mac and only the recognized text is sent to your AI provider for translation. The optional realtime mode streams audio to OpenAI for lower latency, and the app shows a privacy warning before you turn it on.
Which languages does Live Translator support?
The project lists 11 source languages (English, German, French, Spanish, Italian, Japanese, Chinese, Korean, Russian, Arabic and Portuguese) and 12 target languages.
Can Live Translator read translations aloud?
Yes. Text-to-speech can use the free offline Piper voice or the voices of OpenAI and Gemini, which cost money through those providers.
Why does macOS block Live Translator when I open it?
The developer notes that macOS may block the first launch. Right-click the app and choose Open, or run xattr -cr "/Applications/Live Translator.app" in Terminal.
Which permission does Live Translator need?
It needs the Screen & System Audio Recording permission, which macOS asks for the first time the app captures audio.
Where does the Live Translator download on live-translator.FULLMAC.app come from?
The download button leads to the official Live Translator releases page on GitHub at https://github.com/umutcetinkaya/live-translator/releases/latest. live-translator.FULLMAC.app does not change or repackage the app.
Similar Apps
JanJan is a free, open-source app for running AI models on your own Mac. You can download large language models such as Llama, Gemma, Qwen and GPT-oss from Hugging Face and chat with them locally, so everything can stay on your computer. When you want, Jan can also connect to cloud models from OpenAI, Anthropic, Mistral, Groq, MiniMax and others with your own API keys. Custom assistants, a local OpenAI-compatible API server on localhost:1337 and Model Context Protocol support make it useful for agent and developer work too.AI
ClaudeBarClaudeBar is a menu bar app that shows how much of your AI coding quota is left. It reads the limits of the coding assistants you use, such as Claude, Codex, Gemini, Copilot and Cursor, and many more providers including OpenRouter, DeepSeek, Mistral and Windsurf. For each one it shows what is used and what remains, counts down to the next reset and sends a notification before you run out, so you are not stopped in the middle of a task.AI
AionUiAionUi is a desktop app for working with AI agents. It ships with its own agent engine, so it works as soon as it is installed: you paste an API key from Gemini, OpenAI, Anthropic or another of more than 30 supported platforms, or point it at a local model in Ollama or LM Studio. The agent can read and write files, search the web, generate images and use MCP (Model Context Protocol) tools, and 21 ready-made assistants help with tasks such as creating PowerPoint, Word and Excel files.AI
VoiceInkVoiceInk turns your voice into text on the Mac. You press a shortcut, speak, and the transcript is typed into whatever app you are using. Transcription runs locally on your Mac, and optional cloud enhancement can clean up and restructure what you said. Custom words teach it names and terms, Smart Replace expands short phrases you define, and it removes filler words and repetition so your text reads cleanly.AI
SuperwhisperSuperwhisper is a voice-to-text app for the Mac. You press a shortcut, speak, and your words are typed into whatever app you are using, from email and documents to code editors and chat windows. It understands more than 100 languages, can run Whisper speech models locally on your Mac so dictation works offline, and lets you add your own vocabulary so names and technical terms come out right. Modes such as Voice, Message and Email shape the text for the job, and custom prompts let you build your own.AI
FluidVoiceFluidVoice is a dictation app for macOS that turns your speech into text in any app. You press a shortcut, talk, and the words appear in the text field you are using, whether that is an email, a document or a chat box. Speech recognition runs on your Mac with local models, so dictation works offline, and the app is optimized for Apple Silicon. Different modes, such as Write, Command and Dictate, change what happens with what you say.AI
FULLMAC.app does not host this app. Download buttons lead to the developer’s own pages.