skills.rest
kngender5
kngender5COMMUNITY
Explore all skills by this author →
GitHub

voice-input-windows

Set up push-to-talk and always-on ASR voice input on Windows.

Updated Jun 4, 2026
Search Tags:#Windows#ASR#hotkeys#voice input#push-to-talk
One-click install
npx skills add https://github.com/kngender5/hermes --skill voice-input-windows
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice-input-windows
Source: https://github.com/kngender5/hermes/tree/main/skills/productivity/voice-input-windows
Command: npx skills add https://github.com/kngender5/hermes --skill voice-input-windows

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires keyboard, faster-whisper, sounddevice, numpy, pyperclip, win10toast, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a comprehensive setup guide for voice input on Windows, including push-to-talk and always-on ASR functionality.

Core Features & Use Cases

  • Voice Input Setup: Offers instructions for setting up voice input on Windows using Python scripts and global hotkeys.
  • Push-to-Talk: Enables push-to-talk functionality for recording and transcribing voice commands.
  • Always-On ASR: Allows for continuous voice recognition and text typing.
  • Use Case: A user looking to automate tasks or streamline workflows can use this Skill to set up voice input on their Windows system, reducing the need for manual input.

Quick Start

Run the script 'voice_input.py' to start the voice input setup process.

Frequently Asked Questions about voice-input-windows

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up push-to-talk voice input on Windows?▼

Setting up push-to-talk voice input on Windows involves running the voice_input.py Python script, which configures global hotkeys to trigger audio recording and transcription.

What is always-on ASR and how does it work for hands-free control?▼

Always-on ASR enables continuous voice recognition and text typing on Windows by actively capturing audio and transcribing speech into text without requiring manual hotkey activation.

Do I need Python to enable voice recognition and global hotkeys on Windows?▼

Yes, enabling voice recognition and global hotkeys requires Python scripts along with libraries like keyboard and faster-whisper to process audio and manage inputs.

Can I use faster-whisper with sounddevice for transcribing voice commands?▼

You can use faster-whisper with sounddevice for transcribing voice commands by integrating these libraries to record audio from your microphone and perform speech recognition.

What's the best way to automate tasks on Windows using voice commands?▼

Automating tasks on Windows using voice commands is best achieved by configuring push-to-talk or always-on ASR with global hotkeys, allowing you to dictate text and control workflows without manual typing.

Why use pyperclip and win10toast in a Windows voice typing setup?▼

Pyperclip and win10toast are used in a Windows voice typing setup to insert transcribed text into the clipboard for pasting and to display system notifications when recording or transcription states change.

Related Skills

Explore More Software Engineering Skills→
vnmoorthyvnmoorthy
2

setup-gbrain

Install and configure the gbrain CLI with local brain initialization and MCP registration.

Community
Intermediate
reedmayhew18reedmayhew18
23

oc-voice

Transcribe voice chat messages with Whisper and route text downstream.

Community
Intermediate
fellipeutakafellipeutaka
6

tanstack-hotkeys

Manage keyboard shortcuts in React with hotkey registration and sequences.

Community
Basic
surus-latsurus-lat
8

qwen3-asr-howto

Deploy and benchmark Qwen3-ASR models with local, vLLM, or DashScope inference.

Official
Advanced