Last updated
Hybrid speech-to-text CLI tool with offline Whisper support for Windows
$ winget install --id Mantej-Singh.STT-CLI --exact --version 2.0.0Run in Command Prompt, PowerShell, or Windows Terminal. Prompts for any agreements.
For IT teams
App deployment, patching, and remote support in one place. Push this app to every device you manage, keep it patched automatically, and see new CVEs the moment they land. Works with Intune or fully standalone.
Sign up freeFree for up to 5 devices.
STT-CLI v2.0 is a Windows-only speech-to-text tool with hybrid engine support (Whisper offline + Google online). Designed for users on corporate laptops where Win+H is disabled by IT policies. Runs as a background system tray application with no visible window, using a global hotkey (double-tap Left Alt) to toggle recording. Perfect for use with Windows Terminal, PowerShell, Claude Code, and Gemini CLI.
Key Features:
- Hybrid Speech-to-Text: Whisper (offline) + Google Web Speech API (online) with switchable engines
- Offline Mode: Works without internet using OpenAI Whisper (MIT licensed, privacy-focused)
- Engine Toggle: System tray menu to switch between Auto-Detect, Whisper, and Google modes
- About Menu: Version info and engine status at your fingertips
- Auto-start on Windows Boot with persistent settings
- Global hotkey activation (double-tap Left Alt)
- Background operation with system tray icon
- Balloon notifications for recording status and engine changes
- Automatic CLI window detection (security feature)
- No admin rights required
- Portable executable - no installation needed
- Works on corporate laptops with restricted permissions and offline environments
| Architecture | Type | Scope | Install | Download |
|---|---|---|---|---|
| x64 | Portable | - | Direct |
Copy a command tailored to that specific architecture, type, and scope - useful when winget would otherwise pick a different default.
No known CVEs for STT-CLI.
Coverage is best-effort and depends on a winget package mapping to an NVD CPE entry. Absence here is not a guarantee of safety.
More from Mantej Singh Dhanjal or browse speech-to-text, voice-recognition, cli.