100% Offline • Vulkan GPU v1.2.0 Production Release Windows 11 Native

Speak Russian.
Keep English Code.
Zero Cloud. Zero Layout Switching.

Verbum is a commercial-grade local voice dictation tool tailored for developers, engineers, and AI coding agents (Claude Code, VS Code, Cursor, Windsurf, Windows Terminal, Obsidian). Speak Russian naturally with mixed English technical terms, code identifiers, CLI flags, and German terminology — instantly typed into your active application without accidental execution.

verbum // voice injection stream
🎙️ Spoken: "создай функцию calculate_hash которая принимает auth_token и возвращает sha256"
def calculate_hash(auth_token: str) -> str:
[Safe Insertion: Terminal Guard Active • Enter Key Suppressed • Latency: 240ms]

Built for technical flow state.

Standard voice typing fails in code editors because it translates code names, garbles technical English, and triggers accidental commands. Verbum solves this with a purpose-built local architecture.

Dual-Mode Inference

Fast Mode: Sub-300ms single-pass recognition using optimized models for rapid agent prompts.

Accurate Mode: large-v3-turbo-q5_0 with confidence rescue and spoken punctuation for long-form engineering dictation.

🛡️

Zero-Execution Terminal Safety

Never auto-submits dangerous commands. Verbum strictly suppresses Enter, Tab, and control characters in terminal targets (Windows Terminal, PowerShell, WSL, Claude CLI, Codex).

🌐

Zero Layout Switching

Speak Russian sentences with mixed English identifiers, camelCase, snake_case, CLI flags (--check), and German terms. Automatic language detection without manual hotkey toggling.

🔒

100% Offline & Private

Powered by local whisper.cpp with Vulkan GPU acceleration (AMD Radeon, NVIDIA RTX, Intel Arc) with automatic CPU fallback. Zero audio streaming, zero telemetry, zero mandatory cloud accounts.

📋

Safe Clipboard Preservation

Full-format snapshot and restoration for text, rich HTML, DIB bitmaps, and HDROP file paths. Your active clipboard history remains completely untouched during voice injection.

📦

Terminology Packs (.vpack)

Strict resolution hierarchy: Personal Dictionary > Cryptographically Signed .vpack Archives > Core Glossaries. Custom domain dictionaries for IT, backend, devops, and science.

How Verbum compares.

Why developers replace cloud voice APIs and standard OS voice typing with Verbum.

Feature / Capability Verbum v1.2.0 Cloud Whisper / API Windows Voice (Win+H) macOS Dictation
100% Local & Offline Yes (Vulkan GPU) Cloud Streamed Microsoft Cloud ~ Mixed
Zero Layout Switching (RU + EN Code) Native Multi-Vocab ~ Inconsistent Single Language Single Language
Terminal Zero-Execution Guard Hardware-level Lock No Guard May submit Enter No Guard
Safe Clipboard Snapshot/Restore Text + Bitmaps + Files Corrupts Clip N/A N/A
Domain Packs (.vpack) & Custom Glossaries Signed Packs None None None
Latency (Push-to-Talk) ~200–400 ms 800–2500 ms (RTT) ~ 500–1200 ms ~ 400–800 ms
Subscription / Per-Minute Cost 100% Free / Local $0.006/min + API Included Included

System requirements.

Verbum is compiled natively for Windows 64-bit architecture with modern hardware acceleration.

💻

Operating System

Windows 11 (22H2 or newer recommended) or Windows 10 x64 (build 19041+). Native WinUI 3 desktop shell with Mica material support.

🎮

GPU Acceleration

Recommended: AMD Radeon (780M / RDNA2 / RDNA3+), NVIDIA GeForce (RTX / GTX 10-series+), Intel Arc with Vulkan 1.3 support.

CPU Fallback: AVX2 / AVX-512 multi-threaded CPU backend included.

🧠

Memory & Storage

RAM: 8 GB minimum (16 GB recommended for Turbo model).
Disk Space: 2.5 GB free space for bundled models and runtime binaries.

Download Verbum v1.2.0

Standalone, clean Inno Setup installer. Bundled with complete offline STT models, Vulkan GPU engine, and desktop app.

Download Verbum-Setup-1.2.0.exe
📦 Size: ~1.00 GB 🏷️ Version: 1.2.0 🖥️ Platform: Windows x64 📅 Date: August 2026
SHA-256 Checksum: 739a7fcd9717f7b01570794d85feee4b480b0998d0a3ca1a3734b7a336fa5d7e
Verify in PowerShell: Get-FileHash Verbum-Setup-1.2.0.exe -Algorithm SHA256

Frequently asked questions.

Does Verbum send my voice or transcriptions to the cloud? +
No. Verbum runs 100% locally on your machine via a native C++ Vulkan speech recognition backend. It makes zero outbound network calls for audio streaming or recognition telemetry.
How does Verbum prevent accidental command execution in terminals? +
Verbum uses a specialized Win32 input injection sink that explicitly strips newlines and control characters when typing into terminal windows (Windows Terminal, Command Prompt, PowerShell, VS Code terminal). Your transcribed text is typed as a draft, allowing you to review before pressing Enter manually.
What hotkeys are supported? +
Verbum supports both Push-to-Talk (hold key while speaking) and Toggle (press to start, press to stop) modes. Presets include Right Alt, Right Ctrl, Ctrl+Shift+Space, CapsLock, and custom Win32 low-level key bindings with modifier suppression.
How do Terminology Packs (.vpack) work? +
.vpack files are signed, tamper-evident archives containing domain-specific vocabularies (e.g. Kubernetes, React, Python, Machine Learning). When loaded, the terminology engine canonicalizes spoken phrases (e.g. "докер компоуз" → "docker compose") using an exact word-boundary graph with zero hallucination.