Start recording
Tap the dictation hotkey (F8 by default, configurable in Pro Console). A small indicator shows that the microphone is open — and Windows 11 shows its own mic icon too.
New in the Pro beta · Voice input
Voice typing for Windows that never sends your voice anywhere.
Press a hotkey, say what you want to write, and NeuroSwitcher types it into whatever app is focused — chat, browser, editor, IDE. Speech recognition runs on your own PC with downloadable models. No cloud account, no subscription, no audio upload.
- Works offline
- Runs on CPU
- RU · EN · DE + HE beta
- No audio stored
🎙 Recording… (press F8 to stop)
Let's move the meeting to Thursday at three.
Transcribed locally · nothing uploaded
Engine: Running
Model: local ONNX
Hotkey: F8
How it works
Tap the hotkey, talk, tap again. The text lands where your cursor is.
NeuroSwitcher dictation is a small local speech engine that lives next to the layout switcher you already run. It types the recognized text through the same input path used for layout corrections, so it works in ordinary text fields across Windows.
Speak in full phrases
A voice-activity detector splits your speech at natural pauses, so during long dictation the text flows into the app phrase by phrase instead of arriving all at once at the end.
Tap to stop
Tap the hotkey again and the microphone closes. Audio is processed in memory — it is never written to disk and never sent over the network.
Local by design
Why local dictation instead of a cloud service?
Most modern dictation tools stream your voice to a server and charge a monthly fee for it. NeuroSwitcher takes the opposite path: the models run on your machine, so the economics — and the privacy — are different.
Your voice stays home
Everything you dictate — passwords you shouldn't say out loud, work matters, personal messages — is transcribed on your CPU. There is no server to trust, because there is no server.
No subscription meter
Cloud dictation apps pay for compute per minute, so they charge you per month. Local recognition has no per-use cost. Voice input ships as part of the free Pro beta.
Works on a plane
Once a model is installed, dictation needs no internet at all. Spotty hotel Wi-Fi, a train, a locked-down office network — none of it matters.
Models you choose
The installer stays small: recognition models are downloaded on demand from the built-in catalog — one click in Pro Console, with install progress. Pick a small fast model or a larger, more accurate one.
Languages
Built for people who dictate in more than one language.
Like the layout switcher itself, voice input is aimed at multilingual daily work — including sentences that switch language midway.
RussianFull dictation quality with the recommended local model.
EnglishFull dictation quality, including mixed RU/EN sentences in one breath.
GermanFull dictation quality with the recommended local model.
HebrewBeta: works through Whisper models with a language hint; recognition quality is still improving.
A recognition-language setting (Auto / RU / EN / DE / HE) is available in the tray Voice menu and in the Pro Console Voice tab. For Hebrew, setting the language explicitly is recommended.
Dictation cleanup
Raw speech is messy. An optional AI pass tidies it.
Spoken text arrives with filler words, false starts, and missing punctuation. NeuroSwitcher can optionally pass the transcript through a language model — a local one via Ollama or LM Studio, or a cloud model with your own API key — that fixes punctuation and removes the "um, so, actually" before the text is typed.
Cleanup presets
Tidy, Formal, Casual, Bullet list, Summarize, Translate, and more — pick the preset from the tray menu or edit the prompts in Pro Console. Dictate a rambling thought, get a clean paragraph.
Same rules, same privacy
Cleanup is off by default. With a local model it keeps everything on your PC; with a cloud model the text goes directly from your machine to the provider you chose, using your own key. Details on the AI text assistant page.
Control
Managed from the tray or the Pro Console — your pick.
Tray Voice menuStart/stop the engine, switch the active model, and set the recognition language without opening any window.
Voice tab in Pro ConsoleModel catalog with one-click install and progress, engine status, hotkey, and activation settings in one place.
Configurable hotkeyF8 by default; change it if it conflicts with your apps.
Opt-in engineThe voice engine only runs when you start it — it holds the model in RAM, so it stays off until you want it.
FAQ
Common questions about voice input.
Does it work offline?
Yes. After a model is installed, recognition runs entirely on your PC. The only network use around the voice feature is downloading a model when you explicitly install one.
Is my voice recorded or stored?
No. The microphone is open only between an explicit start and stop, the audio is transcribed in memory, and nothing is written to disk or uploaded. While recording, both the NeuroSwitcher indicator and the standard Windows microphone icon are visible.
Do I need a powerful PC or a GPU?
No. Dictated phrases are short, and the default models transcribe them faster than real time on an ordinary CPU. Larger, more accurate models are available in the catalog if your machine can handle them.
Which apps does it work in?
Any app with a normal text field: browsers, chats, editors, IDEs, office apps. The text is typed through the same input path NeuroSwitcher uses for layout corrections, and the same per-app exclusion list applies.
How good is Hebrew?
Hebrew dictation is in beta. It works through Whisper models with the language explicitly set to Hebrew, and the output is real Hebrew text, but recognition quality is noticeably behind Russian, English, and German for now. This is being actively worked on.
Is voice input free?
Voice input is part of the free Pro beta. The managed model catalog with one-click install is a Pro convenience; the underlying voice engine is part of the open core.
Free Pro beta
Type with your voice. Keep your voice to yourself.
Download NeuroSwitcher for Windows 10 and 11, open the Voice tab, install a model in one click, and dictate into any app — offline.
Download NeuroSwitcher