← All Comparisons

Voxtype vs Speech Note

A daemon vs a GUI app. Push-to-talk dictation vs multi-purpose transcription tool.

At a Glance

Aspect Voxtype Speech Note
Interface Daemon (CLI) GUI application
Engines Whisper VOSK, Whisper, Coqui, more
Cursor Injection Yes (ydotool) No (clipboard only)
Recording Feedback Audio + Notifications Visual (in-app only)
GPU Acceleration Vulkan, CUDA, Metal, ROCm No
Text Processing Word replacements, spoken punctuation No

Critical Differences

Cursor Injection vs Clipboard

Voxtype types text directly at your cursor. Hold key, speak, release—text appears where you're working.

Speech Note copies text to clipboard. You must switch to your target application and paste every time. For inline dictation while writing, this adds significant friction.

Recording Feedback

Voxtype plays audio cues and sends desktop notifications. Works even when you're not looking.

Speech Note shows recording status in its GUI window only. If minimized or behind other windows, you won't see it.

Different Tools for Different Jobs

Voxtype: The Dictation Daemon

Laser-focused on one thing: hold a key, speak, release, text appears at your cursor. Always running, always ready.

Speech Note: The Transcription Suite

A full-featured application for:

When to Use Each

Use Case Best Tool
Dictating emails while writing Voxtype
Quick notes in any application Voxtype
Transcribing audio files Speech Note
Comparing STT engines Speech Note
Text-to-speech needs Speech Note
Translation workflows Speech Note

Engine Options

Voxtype (Whisper only)

Uses whisper.cpp for offline inference. One engine, optimized integration, excellent accuracy out of the box.

Speech Note (Multiple engines)

Speech Note lets you experiment to find what works best for your voice and hardware.

Workflow Comparison

Voxtype Workflow

[Hold Right Ctrl] → [Speak] → [Release] → Text appears at cursor

Never leave your application. Never move your hands from keyboard.

Speech Note Workflow

[Switch to Speech Note] → [Click Listen] → [Speak] → [Copy] → [Switch back] → [Paste]

Or use global keyboard shortcuts (requires accessibility settings).

Installation

Voxtype

curl -LO https://github.com/peteonrails/voxtype/releases/download/v0.2.1/voxtype_0.2.1-1_amd64.deb
sudo dpkg -i voxtype_0.2.1-1_amd64.deb
voxtype setup model
voxtype setup systemd
systemctl --user enable --now voxtype

Speech Note

flatpak install flathub net.mkiol.SpeechNote
flatpak run net.mkiol.SpeechNote

The Recommendation

Want inline dictation while you work? Voxtype

Want a GUI for transcription, TTS, and translation? Speech Note

Want both capabilities? Install both. They complement each other perfectly.

Links