Desktop Local Mode on Windows, macOS, and Linux

Offline-Transkription auf Ihrem eigenen Rechner

Transkribieren Sie Audio und Video ohne Internetverbindung. Die LiteScribe Desktop-App führt Spracherkennung und KI-Notizen im Local Mode auf Ihrer eigenen CPU oder GPU aus, sodass niemals Audio Ihren Rechner verlässt.

Offline-Transkription wandelt Audio auf Ihrem eigenen Computer in Text um, ganz ohne Internetverbindung. Die LiteScribe Desktop-App für Windows, macOS und Linux bringt einen Local Mode mit, der lokale Spracherkennung und ein lokales KI-Modell für Zusammenfassungen und Notizen ausführt. So verlässt kein Audio Ihren Rechner, und kein externer Anbieter sieht Ihr Transkript. Das Transkript selbst wird mit Ihrem LiteScribe-Konto synchronisiert, sofern Sie das nicht abschalten. Local Mode ist in den Tarifen Pro und Business enthalten, nach einem einmaligen Modell-Download.

Get the desktop app See Pricing

Was Offline-Transkription wirklich bedeutet

Offline-Transkription ist Spracherkennung, die vollständig auf Ihrer eigenen Hardware läuft, ohne dass Audio an einen Server gesendet wird. Bei LiteScribe heißt das Local Mode, und es steckt in der Desktop-App für Windows, macOS und Linux. Wenn der Local Mode aktiv ist, wandelt die App Ihre Aufnahme mit einer lokalen Spracherkennung in Text um und lässt ein lokales KI-Modell Zusammenfassungen und Aufgaben schreiben, alles auf Ihrer CPU oder GPU. Die Web-App und die mobile App haben diesen Weg nicht; sie nutzen Cloud-Transkription, daher ist Offline-Transkription eine reine Desktop-Funktion.

The practical difference is where the work happens. In the normal cloud path your audio is uploaded and processed by a transcription service, then an AI provider summarizes the text. In Local Mode neither step leaves your machine. That matters when you are on a plane with no Wi-Fi, on a locked-down corporate network, or simply working with a recording you would rather not upload anywhere.

Transcription and AI, both on-device

Local Mode is not just offline transcription. The same on-device path also runs the AI that turns a raw transcript into something useful. After your audio is transcribed locally, an on-device language model generates the summary, the action items, and the cleaned-up notes, again without a network call. So a meeting you record offline comes back as a transcript with speaker labels and a structured set of notes, produced start to finish on your own computer.

The app picks a model that fits your hardware. It accelerates on the GPU when you have one, using CUDA on NVIDIA cards, Vulkan on AMD and Intel, and Metal on Apple Silicon, and it falls back to the CPU when no compatible GPU is present. You choose a model size to trade speed against quality, and larger models give better results on capable machines.

What still needs the network, stated plainly

Offline transcription keeps your audio on your device, but the desktop app is not permanently disconnected, and we will not pretend it is. The on-device models are a one-time download the first time you turn Local Mode on. After that, the app reconnects to LiteScribe periodically to confirm your plan and your remaining minutes; if it has not been able to check in for a couple of days it pauses new offline work until the next reconnect. That check validates your account, not your content.

So the accurate way to think about it is by data path. Your audio stays on your machine in Local Mode, without exception, and no transcription service or outside AI model ever receives your transcript, because both of those run on your own hardware. What the finished transcript does do, by default, is sync to your own LiteScribe account so you can read it on your phone or in a browser. If you would rather it did not, turn off "Sync new local transcripts to cloud" in Settings, Privacy, and every new recording stays on this computer only. You can also lock an individual transcript, or mark every existing one private in a single action.

Why use LiteScribe Local Mode

No internet needed to transcribe

On-device speech recognition runs on your CPU or GPU, so you can transcribe a recording with the Wi-Fi off once Local Mode is set up.

Audio never leaves your device

In Local Mode your audio is not uploaded at all, and no outside transcription or AI provider ever receives your transcript.

On-device AI notes

A local language model writes summaries and action items on your machine, so the AI step is offline too.

GPU accelerated

CUDA, Vulkan, or Metal acceleration with an automatic CPU fallback, so it stays fast on the hardware you have.

Offline-Transkription auf Ihrem eigenen Rechner

1
Install the desktop app
Download LiteScribe for Windows, macOS, or Linux and sign in. Local Mode is part of the desktop app on the Pro and Business plans.
2
Turn on Local Mode and download a model
In settings, enable Local Mode and download an on-device transcription model and an optional AI model. This one-time download is the only step that needs the network.
3
Transcribe offline
Pick a file or record, and the app transcribes on your CPU or GPU with speaker labels. No audio is uploaded while Local Mode is on.
4
Get on-device notes
The local AI model writes a summary and action items on your machine. The transcript syncs to your LiteScribe account for cross-device access unless you turn that off in Settings, Privacy.

What is private, and what is honest

Privacy on this page means the desktop Local Mode, where your audio is transcribed on your own CPU or GPU and an on-device AI model writes your notes, so your recording is never uploaded and no outside provider ever sees your transcript. The web app, the mobile app, and the cloud path are different: they use a cloud transcription service and cloud AI, so they are not private in this sense. Local Mode is a desktop feature on the Pro and Business plans, available for Windows, macOS, and Linux after a one-time model download.

We will not call the app air-gapped, because it is not. Your audio stays on your device, but the desktop app reconnects to LiteScribe periodically to validate your plan and remaining minutes, and it pauses new offline work if it cannot check in for about two days. That account check carries none of your content. One more thing worth saying plainly: the finished transcript syncs to your own LiteScribe account by default, so you can read it on your other devices. Turn off "Sync new local transcripts to cloud" in Settings, Privacy, or lock an individual transcript, and the text stays here with the audio.

Local Mode Privacy and security Privacy policy

FAQ

Frequently Asked Questions

Ja, in der Desktop-App. Wenn der Local Mode aktiviert und die lokalen Modelle heruntergeladen sind, laufen Transkription und KI-Notizen ohne Internetverbindung auf Ihrer eigenen CPU oder GPU. Die Web-App und die mobile App nutzen Cloud-Transkription und benötigen eine Verbindung.

No. Offline transcription is a desktop-only feature, available in the LiteScribe app for Windows, macOS, and Linux. The web app and mobile app transcribe in the cloud.

Your audio stays on your device, but the app is not air-gapped. It downloads the on-device models once, then reconnects periodically to validate your plan and remaining minutes. If it cannot check in for about two days, new offline work pauses until the next reconnect. Your finished transcript also syncs to your LiteScribe account by default, which you can switch off in Settings, Privacy.

Offline transcription, part of Local Mode, is available on the Pro and Business plans. It is a desktop-only feature with a one-time on-device model download.

No. The app detects your hardware and picks a model tier that fits your RAM and VRAM, with a CPU fallback. A GPU using CUDA, Vulkan, or Metal makes it faster, but it is not required.

On-device transcription is high quality, and larger local models are more accurate. For the very best accuracy you can switch any recording back to the cloud path. Local Mode trades a little accuracy for keeping your audio on your machine.