Show HN: Speak to AI – offline speech-to-text for Linux (alternative to Dragon)

A minimalist, privacy-focused desktop application for offline speech-to-text. Converts voice input directly into any active window (editors, browsers, IDEs, AI assistants) Uses the Whisper model locally for speech recognition. Written in Go, an optimized desktop application for Linux.

• Offline speech-to-text and voice typing
• Portable: AppImage package
• Cross-platform support for X11 and Wayland
• Desktop Environment Support: Native integration with GNOME, KDE, and other Linux DEs
• Privacy-first: desktop, no data sent to external servers
• Support: multi-language, global hotkeys, automatic typing & clipboard, system tray integration, visual notifications, WebSocket API (optional)

Download the latest AppImage from Releases:

Help us test different desktop environments:

📋 Desktop Environment Support Guide

For system tray integration on GNOME, install the AppIndicator extension ↑

KDE and other DEs have built-in system tray support out of the box

For automatic typing on Wayland (GNOME and others) — set up ydotool ↑

X11 has native typing support with xdotool out of the box

If automatic typing doesn't appear automatically, the app falls back to clipboard (Ctrl + V) mode

AppImage release - main distribution format. I'd appreciate feedback about your experience on your system!

Flatpak bundle is planned.

For issues and bug reports: GitHub Issues

See changes: CHANGELOG.md

Start onboarding with:

• ARCHITECTURE.md — system architecture and component design
• DEVELOPMENT.md — development workflow and build instructions
• CONTRIBUTING.md — contribution guidelines and how to help improve the project
• docker/README.md — Docker-based development

• OS: Linux (Ubuntu 20.04+, Fedora 35+, or similar)
• Desktop: X11 or Wayland environment
• Audio: Microphone/recording capability
• Storage: 277.2MB (whisper small q5 model, dependencies, go-binary)
• Memory: ~300MB RAM during operation
• CPU: AVX-capable processor (Intel/AMD 2011+)

• whisper.cpp for the excellent C++ implementation of OpenAI Whisper
• fyne.io/systray for cross-platform system tray support
• OpenAI for the original Whisper model

Sharing with the community for privacy-conscious Linux users

MIT — see LICENSE.

If you find Speak-to-AI useful, please consider supporting development.