Real-time speech translationfor every conversation

Übersetz is free, with no subscriptions, advertisements or tracking inside the app. The Mac, iPhone, iPad and Android editions are available to download. If you choose GPT Realtime, Gemini Live or another remote provider, that provider may charge for API usage under its own pricing. Donations are optional and help fund continued development, testing and model support.

The disk image is larger than a typical utility because it includes the macOS app plus on-device speech-recognition and speaker-processing assets. Those components let Übersetz hear and prepare live audio locally instead of making every session depend on an Übersetz server. The installer does not contain every Qwen translation model. Local translation models are separate downloads, so you install only the model that suits your Mac and available memory.

The Mac edition supports GPT Realtime, Gemini Live Translate Preview, Apple Translate on compatible macOS versions, managed Qwen downloads, compatible models installed in local Ollama, and custom Ollama or OpenAI-compatible endpoints. Mobile editions use platform-specific processing paths. The app shows the providers and language paths available for your device; Android also checks Google on-device capability for the selected device and language.

Yes. GPT Realtime Translate is optional and requires an OpenAI API key that belongs to you. Übersetz does not include shared OpenAI access or bundle API usage with the free download. You create and manage the key in your own OpenAI developer account, then add it in the app’s settings. OpenAI usage and billing are governed by your OpenAI account.

Gemini Live Translate is an opt-in Preview provider. It requires your own Google Gemini API key, internet access, a supported target language and acceptance of the in-app provider disclosure. The Google key is stored separately from the OpenAI key in macOS Keychain. Google may require project access or billing, may impose quota, and may change Preview model availability. Übersetz does not silently switch to GPT or another provider if Gemini fails.

Yes, when you select an on-device path supported by your platform, device and language. The Mac edition can use managed local models or Apple Translate; iPhone, iPad and Android use their platform-native paths where supported. Übersetz does not operate a processing server for those workflows and does not create a raw-audio archive. If you explicitly select GPT Realtime, Gemini Live or a remote endpoint, the chosen provider receives the data required to perform that service and its own terms apply.

No screen pixels are captured. System audio is received through a macOS audio tap, so Übersetz can hear supported audio without reading or transmitting the screen. The app does not save raw microphone or system audio. It does retain the current transcript and Advisor state locally in Application Support so the session can be restored after relaunch. Clear removes that retained session; Save creates a separate Markdown export at the destination you choose.

The Mac edition requires macOS 15 or later and Apple silicon. Android requires Android 12 or later; on-device speech and translation availability varies by device and language. For iPhone and iPad, see the App Store listing for the current device and operating-system requirements.

The app download includes the core speech assets, but translation models are installed separately. You initiate a managed Qwen download or choose Add local model to pull a catalogue or advanced tag through a running local Ollama service. This avoids bundling several gigabytes of models in the installer. Managed Qwen downloads range from roughly 1 GB to more than 16 GB; catalogue sizes vary and Ollama manages those files.

Übersetz is designed for multilingual speech and lets you enable the languages relevant to you. Coverage and quality depend on the selected transcription and translation model, and not every language performs equally well with every provider. GPT Realtime, Gemini Live, Apple Translate, local models and custom endpoints can have different strengths and target-language lists. For important conversations, test the exact source, target and model combination you plan to use.

On Mac, yes: Übersetz can listen to your microphone, system audio, or both, so it can follow supported meetings, calls, videos and live streams without a dedicated integration for each app. The mobile editions are microphone-first and do not claim general system-audio capture. Audio availability still depends on platform permissions and the source application.

The initial app and model downloads require internet access. After the required assets are installed, supported on-device workflows can process a conversation without an Übersetz processing server. GPT Realtime, Gemini Live and remote custom endpoints require a network connection. Apple or Google language assets may need to be downloaded before offline use, and exact offline support varies by platform, device, language and model.

Übersetz is available for Mac, iPhone, iPad and Android. Download the Mac edition directly from this site, the iPhone and iPad edition from the App Store, and the Android edition from Google Play. Available features and operating-system requirements can differ by edition.