# Voxtype

> Open-source push-to-talk dictation for Linux and macOS

Voxtype is a free, open-source push-to-talk dictation tool for Linux and macOS. Hold a hotkey, speak, and release, and the transcript is typed at the cursor or placed on the clipboard. It runs as a background daemon that is set up from the terminal, with a choice of speech engines that run on the machine, including Whisper, Parakeet and Cohere Transcribe. A meeting mode transcribes longer recordings with speaker attribution and export.

- **Category:** Voice Dictation
- **Made by:** Peter Jackson (Faster Agile)
- **Website:** https://voxtype.io
- **Runs on:** macOS, Linux
- **Facts last checked:** Oct 6, 2026

## Pricing

Voxtype is free to use.

- **Pricing model:** Free
- **Free plan:** Entirely free and open source under the MIT License, with no subscription, cloud service or telemetry. The maintainer says he does not accept donations.
- **Free trial:** None listed.

| Plan | Price | What you get |
| --- | --- | --- |
| Voxtype | $0 | The full tool for Linux and macOS with every engine and meeting mode, installed from the AUR, a .deb or .rpm package, Nix, an AppImage or Homebrew. |

Read from https://voxtype.io/ on Oct 6, 2026. Prices change, so confirm with Voxtype before buying.

## Key features

- **Push-to-talk at the cursor:** Hold a hotkey, ScrollLock by default, speak and release, and the text is typed at the cursor, with the clipboard as a fallback. A toggle mode starts and stops with one press each.
- **Nine local speech engines:** Whisper, Parakeet, Moonshine, SenseVoice, Paraformer, Dolphin, Omnilingual, Cohere Transcribe and OpenVINO Whisper are switched with one config line. Models load on first use and unload when idle.
- **GPU and NPU acceleration:** Whisper runs on Vulkan across GPU vendors, the ONNX engines use CUDA 12 or 13 on NVIDIA and MIGraphX on AMD cards, and OpenVINO runs Whisper on Intel NPUs.
- **Meeting mode:** Continuous transcription with automatic chunking and speaker attribution for meetings and interviews, stored locally and exported to Markdown, plain text, JSON, SRT or VTT.
- **Text processing:** Spoken punctuation turns words such as "comma" into symbols, replacement tables fix common mistranscriptions, and an optional command pipes the transcript through a local LLM or a shell script.
- **Linux desktop integration:** Compositor keybindings cover Hyprland, Niri, Sway, River, GNOME and KDE, with an evdev fallback for X11. It pauses MPRIS media players while recording and shows a floating waveform.

## Good for

- Linux users on Wayland desktops such as Hyprland, Sway or GNOME
- People comfortable setting up a tool from the terminal
- Dictating prompts into terminals, editors and coding agents

## Worth knowing

- There is no Windows or mobile version; packages cover Linux and macOS only.
- Setup happens in the terminal: it runs as a daemon, and on Linux the hotkey is bound in the compositor or needs the user added to the input group.
- Prebuilt Linux packages need a recent distribution, such as Ubuntu 24.04, Debian Trixie or Fedora 40 or later.
- Grammar cleanup and meeting summaries are not built in; they rely on a separate tool such as Ollama that you install yourself.

## Works with

Ollama, LM Studio, Soniox, Waybar

**Tags:** Dictation, Transcription, Meeting notes, Open source, Works offline, Local-first

## Alternatives

- [Handy](https://toolgpa.com/tools/handy): Free, open-source offline speech-to-text for desktop. [Compare](https://toolgpa.com/compare/handy-vs-voxtype)
- [Whispering](https://toolgpa.com/tools/whispering): Open-source dictation app that uses your own models or API keys. [Compare](https://toolgpa.com/compare/voxtype-vs-whispering)
- [OpenWhispr](https://toolgpa.com/tools/openwhispr): Open-source dictation with free local models and meeting notes. [Compare](https://toolgpa.com/compare/openwhispr-vs-voxtype)
- [Talon](https://toolgpa.com/tools/talon): Hands-free computer control by voice, eye tracking and noises. [Compare](https://toolgpa.com/compare/talon-vs-voxtype)
- [Spokenly](https://toolgpa.com/tools/spokenly): Dictation app with free local models and optional cloud accuracy. [Compare](https://toolgpa.com/compare/spokenly-vs-voxtype)

## Sources

The prices, plans, platforms and features above were read from these pages on Oct 6, 2026:

- https://voxtype.io/
- https://raw.githubusercontent.com/peteonrails/voxtype/main/README.md

Page: https://toolgpa.com/tools/voxtype
Listed by ToolGPA (toolgpa.com).