Use this command to install VoiceWave Local Core with WinGet:
winget install --id=VoiceWave.LocalCore -e
VoiceWave Local Core is a privacy-first desktop dictation application designed for seamless speech-to-text transcription on Windows. It captures audio locally, processes it using whisper.cpp models without sending data to external servers, and inserts transcribed text directly into applications with reliability.
Key Features:
Local Transcription: All processing occurs on-device, ensuring no audio leaves your machine.
Global Hotkey Control: Use push-to-talk or toggle dictation with customizable hotkeys for efficient input.
Direct Text Insertion: Reliably inserts transcribed text into the active application, with clipboard and history fallbacks to ensure accuracy.
Verified Model Management: Ensures Whisper models are validated through checksums for consistent performance.
Audience & Benefit:
Ideal for privacy-conscious users, developers, and professionals on Windows seeking reliable, offline transcription. VoiceWave Local Core offers a secure alternative to cloud-based dictation tools, prioritizing user data protection while maintaining high accuracy and responsiveness.
Install VoiceWave Local Core via winget with ease.
README
Free and open source · Works offline after a one-time model download · English
How it works
Hold Ctrl + Win and talk. Double-tap the shortcut to go hands-free; Escape cancels.
Let go. Your speech is transcribed on your PC: on the graphics card through Vulkan
when it qualifies, otherwise on the CPU.
The text lands at your cursor, in whatever app you were using.
What you get
Never leaves your PC
There is no VoiceWave server and no account. Audio stays in memory and is transcribed on your
machine. VoiceWave goes online for three things only:
Model downloads, once: the speech model at setup, and the AI polish model if you turn it on.
Update checks against GitHub. Updates are signed and verified before they install.
An anonymous usage count, on by default, which you can turn off during setup or in
Settings → Diagnostics. What it sends
AI polish, on your machine
Optional and off by default. A small local model (Qwen2.5 1.5B through llama.cpp) tidies fillers,
casing and punctuation, with profiles for Standard, Coding and Writing (Literal skips it). A
fidelity check rejects rewrites that drift from what you said and keeps the plain transcript
instead. It is a one-time download of about 1 GB and needs a CPU with AVX2.
Install
Download VoiceWave.Local.Core__x64-setup.exe from the
latest release
and run it.
Windows may warn "Windows protected your PC" (Unknown publisher). The installer is not
code-signed yet, so SmartScreen does not recognise it. Choose More info → Run anyway. Every
installer is built in public by GitHub Actions from this
repository, and in-app updates are signed and verified before they install.
First launch checks your microphone and downloads one speech model, chosen for your PC:
about 488 MB (Small) up to 1.6 GB (Large Turbo). After that, dictation works offline.
> [!NOTE]
> winget install VoiceWave.LocalCore also works, but the winget listing currently trails the
> latest release. Use the installer above to get the newest version.
Requirements
Needs
Windows
10 or 11, 64-bit
CPU
x64 with SSE4.1. AVX2 is needed for the GPU engine and AI polish.
GPU (optional)
A discrete NVIDIA, AMD or Intel graphics card with Vulkan 1.2. PCs with only integrated graphics use the CPU engine for now.
Language
English
Compared with cloud dictation
VoiceWave
Wispr Flow
Price
Free
$15/month for Pro; free tier capped at 2,000 words/week
On by default for new installs since 0.6.1 (existing users were asked once). It helps show whether
people get through setup and whether dictation works for them. Turn it off during setup or in
Settings → Diagnostics. It is sent through TelemetryDeck with a
random installation ID, the app version and the download channel, and counts only:
your first successful dictation, and whether it ran on the GPU or the CPU;
one "active today" marker per day;
which setup step you reached, and whether setup finished or was skipped;
a speech or AI polish model download failing;
the GPU engine falling back to the CPU, with a reason category.
It never sends audio, transcript text, dictionary or snippet content, account details, file names
or settings.
What's new in 0.7.0
GPU dictation on any vendor. whisper.cpp runs on discrete NVIDIA, AMD and Intel graphics
cards through Vulkan, in its own worker process. No CUDA download.
Picked per PC. A one-time check confirms the GPU works before VoiceWave switches to it, and
dictation steps down to the CPU automatically if the GPU misbehaves.
Verified GPU models. whisper.cpp models are checked against pinned SHA-256 hashes before
they replace anything.
Something not working? In the app, Help → Report a problem opens a pre-filled GitHub issue
with your app version, Windows version and speech engine. You can also
open an issue
directly. Logs never contain what you dictated.
npm install
npm run tauri:dev # desktop app (needs the Rust + Tauri prerequisites)
npm run dev # interface only, in a browser
npm test # frontend tests
npm run build # type-check and build the interface
The release build stages the Python runtime and the whisper.cpp workers; see
release.yml and the scripts under
scripts/. More in CONTRIBUTING.md.
