BuildWithAIsBuildWithAIsOfficialยท3 Agent Skills Included

voicekey

Private push-to-talk voice typing for any desktop app

Transcribes speech locally on your device and inserts the text directly into whatever application you are using. Eliminates manual typing, cloud transcription fees, and privacy risks from uploading audio to third-party servers. Adds optional text cleanup and translation with your own language model provider, plus searchable local history for up to 90 days.
npx skills add BuildWithAIs/voicekey --all -g -y
Available:

Tells your AI coding agent how the Electron app is structured, which README files to read before editing code, and what security and style rules to follow when making changes.

All Skills in This Repository (3)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install Voice Key?โ–ผ

Run `npx skills add BuildWithAIs/voicekey --all -g -y` in your terminal to install everything globally. You can also download the ready-made Windows, macOS, or Linux installer from the GitHub Releases page.

Does Voice Key send my audio to the cloud?โ–ผ

No. Speech recognition runs entirely on your device using downloadable local models, so raw audio never leaves your computer.

How does push-to-talk voice typing work?โ–ผ

Hold the hotkey, speak, and release. Voice Key transcribes your speech and pastes the text into whichever app currently has focus.

Can Voice Key clean up or translate my text?โ–ผ

Yes. You can connect your own OpenAI, DeepSeek, or OpenRouter API key to refine transcripts or translate selected text in place.

Which platforms does Voice Key support?โ–ผ

It runs on Windows, macOS (Intel and Apple silicon), and Linux, including a managed Hyprland integration for Omarchy and Arch users.

Related Repositories in Personal & Entrepreneur

View All in Personal & Entrepreneurโ†’