Verbtm Logo
Verbtm v0.2.0
Verbtm 0.2.0 Released — 100% Free & Private

Voice to text, at the
speed of thought.

Zero cloud. Zero telemetry. Instant keyboard injection into any Windows app with local Whisper speech recognition.

Download for Windows
v0.2.0 • 64-bit • Setup.exe
Explore Features
First install: If Windows SmartScreen prompts, click More infoRun anyway.
CUDA 12 & cuDNN GPU Acceleration
100% Local / Zero Cloud Telemetry
Native Win32 SendInput (Zero Clipboard Impact)
Dynamic Island Simulator Interactive Preview
Ready
Ctrl + Win to dictate
Simulates global Push-to-Talk shortcut (Ctrl + Win)
// Active Focus: Cursor / VS Code / Browser / Slack Win32 SendInput Ready
Hold the button above or switch states to test transcription...
Switch Theme Accent:

Engineering First

Built for developers, writers, and privacy purists.

Verbtm gives you the speed of modern deep learning without surrendering your conversations to third-party clouds.

100% Local & Private

Fast-Whisper neural models run entirely on your local GPU or CPU. No audio bytes or transcripts ever leave your device. Fully functional even when completely offline.

Universal Win32 Typing

Uses native Win32 batch SendInput with UTF-16 surrogate safety. Injects text into whichever application has focus without altering your clipboard.

Fluent Dynamic Island

A sleek, floating OLED-style pill HUD that stays cleanly docked at the top of your screen. Displays real-time 16-band audio levels and processing status without stealing window focus.

CUDA 12 & cuDNN 9 Speed

Compiled directly against NVIDIA CUDA 12 and cuDNN 9 libraries. Transcribes 10 seconds of speech in under 350 milliseconds on modern RTX GPUs, with auto-fallback to AVX2 CPU.

Smart Hallucination Filter

Eliminates Whisper repetition loops with custom n-gram deduplication, hallucination silence thresholding, and built-in Voice Activity Detection (VAD).

Customizable & Lightweight

Pick between Push-to-Talk or Toggle mode. Choose from 6 WinUI 3 color presets, select your audio microphone device, and calibrate transcription sensitivity in seconds.

Native Windows Design

Crafted for Fluent Dark. Designed for speed.

Verbtm feels like an integrated part of Windows 11. Enjoy fine-grained control over speech models, audio input hardware, visual themes, and global hotkeys.

Multiple Whisper Models: Run lightweight tiny or base for ultra-low latency, or switch to small for studio-grade accuracy.
6 Built-in Color Themes: Match your desktop aesthetic with Neon Sunset, Cyberpunk, Emerald Matrix, Solar Flare, Amethyst, and Ice & Silver.
Hardware Audio Selector: Explicitly bind to your preferred USB or XLR microphone without touching Windows defaults.
Verbtm Settings Window Preview

Why Verbtm

How Verbtm stacks up against alternatives.

Feature Verbtm Cloud AI Dictation Built-in Voice Typing
Audio Privacy 100% Local (Never leaves PC) Sent to Cloud Servers Sent to Cloud Servers
Subscription Cost 100% Free & Local ($0) $15 – $30 / month Free with OS
Air-Gapped / Offline Yes (Fully Functional) No (Requires Internet) No (Requires Internet)
Text Injection Method Direct Win32 Keystroke Often overwrites clipboard Direct Keystroke
Hallucination Guard Smart VAD + Repetition Penalty Varies by service Limited
Visual HUD Fluent Dynamic Island Standard Window / None Windows Floating Bar

Hardware & Compatibility

Runs on modern laptops, rigs, and workstations.

Minimum Requirements

CPU Fallback
  • OS: Windows 10 or Windows 11 (64-bit)
  • Processor: Intel Core i5 (8th Gen+) or AMD Ryzen 5 (AVX2)
  • Graphics: Integrated or Dedicated GPU (CPU INT8 fallback)
  • Memory: 4 GB RAM
  • Storage: 2 GB free disk space
  • Microphone: Any functional input device (USB, 3.5mm, Bluetooth)
  • Latency: ~250–400ms transcription speed
Recommended

Optimal Performance

Instant GPU
  • OS: Windows 11 (64-bit)
  • GPU: NVIDIA GeForce GTX 16-series / RTX Series (CUDA 12)
  • VRAM: 4 GB+ dedicated VRAM
  • Memory: 8 GB+ RAM
  • Storage: 3 GB free disk space (fast SSD recommended)
  • Latency: ~60–90ms instant transcription (sub-100ms)

Smart Hardware Detection: The installer automatically identifies whether your system has an NVIDIA GPU or standard CPU, seamlessly deploying the optimal acceleration engine without requiring any manual driver setup.

Answers

Frequently Asked Questions

Is Verbtm free to use?

Yes. Verbtm is 100% free to download and use for all personal and professional workflows. Speech recognition runs offline on your local GPU or CPU with zero cloud subscriptions and zero data collection.

Does it need an active internet connection?

Only once during the very first run to fetch your chosen Whisper speech model (e.g., ~140 MB for base.en). Once cached, Verbtm operates 100% locally and completely offline—no audio streams, telemetry, or transcripts ever leave your PC.

How does text injection work without overwriting my clipboard?

Verbtm utilizes native Win32 SendInput keystroke synthesis. It types transcribed characters directly into whatever window currently has focus (VS Code, Word, Chrome, Slack, Discord) just as if you typed them on a mechanical keyboard.

What if my computer doesn't have an NVIDIA GPU?

Verbtm runs smoothly on standard Intel and AMD systems. During setup, it detects your hardware and automatically enables optimized multi-threaded CPU inference with INT8 quantization, giving you responsive (~250–400ms) dictation without requiring a dedicated graphics card.

How can I verify my privacy if the application code is private?

Verbtm is distributed as a verified standalone application to prevent malicious third parties from creating compromised clones bundled with keyloggers.

Privacy is guaranteed and verifiable directly at the network layer:

  • Self-Contained Installer: The setup installer is 100% offline, bundling all application files and CUDA libraries with zero installer-side network downloads.
  • One-Time Model Fetch: The only network request the application ever makes is on initial run to download your chosen Whisper speech model (e.g., ~140 MB for base.en) directly to your local drive. After that, speech recognition operates 100% offline.
  • Zero Telemetry: No analytics trackers, advertising IDs, or background telemetry beacons are bundled.
  • Auditable Network Traffic: You can block Verbtm.exe in Windows Defender Firewall or inspect it with Wireshark to confirm that zero audio or keystroke packets ever leave your PC.

Why does Windows SmartScreen or Edge show a download warning?

Microsoft Defender SmartScreen flags newly released executables that haven't yet accumulated widespread global download telemetry. Verbtm is completely safe, private, and 100% offline.

If prompted in Edge, click KeepKeep anyway. When launching the installer, click More infoRun anyway.

Dictate faster. Protect your privacy.

Download Verbtm today. No credit cards, no logins, no cloud tracking.

If SmartScreen or Edge flags the download, choose Keep and Run anyway.