§ Linux · Omarchy
Dettivo for Linux
Dettivo for Linux is the free, open-source edition for Omarchy, Hyprland, Sway and Niri. These pages go from the pacman install to your first dictation, then cover models, meetings, the `dettivo` CLI and MCP. The GitHub repository holds the full reference.
CLI · MCP
CLI and MCP on Linux
The `dettivo` command reaches everything the app does and prints JSON with `--json`. One more command registers Dettivo as an MCP server in Claude Code, Codex, Cursor or Claude Desktop, with nineteen tools to search transcripts, insert text or start a dictation.
Developer toolLocal-onlyFirst run
First run on Linux
Open Dettivo from the launcher. If something is missing, three screens walk you through it: Keys, Models and Try it. After that the app opens on Home, and holding F9 dictates into any window.
Linux install
Install Dettivo on Linux
Download the pacman package from the latest GitHub release, then three commands put Dettivo on an Omarchy machine: pacman installs the package, systemctl enables the daemon, and `dettivo setup omarchy` binds the keys and adds the bar plugin and the recording pill.
Local-onlyKeys + dictation
Keys and dictation on Linux
Hold F9, talk, let go. The text lands in the window that had focus when you pressed the key. On Omarchy these are the chords Omarchy already binds for dictation, so there is nothing to relearn.
Meetings
Meetings on Linux
Start a meeting from the app, the bar panel or `dettivo meetings start`. Dettivo records your microphone and the call's audio as two tracks and transcribes while you talk. At stop it names the speakers and writes a summary with decisions and action items. Nothing joins the call.
Local-onlyModels
Models on Linux
Dettivo for Linux runs whisper.cpp and parakeet.cpp for speech, llama.cpp for Enhanced and meeting analysis, and sherpa-onnx to tell speakers apart. Every model runs on your machine, on a Vulkan GPU or on the CPU.
Local-onlyWhen something breaks
Troubleshooting on Linux
Start with `dettivo doctor`. It checks the service, the socket, the configuration, every engine and its backend, the insertion chain, the hotkeys, the history store and the pill, and names what is missing.
- Getting started Install, activate, grant permissions, and run your first dictation.
- Dictation Hotkeys, modes, direct insertion, dictionary, Quick Access, Quick Note.
- Meetings Bot-free capture, speaker labels, meeting analysis, recap automation, Meeting Mirror.
- Automation Dictation macros, app + shell allowlists, recap email automation, weekly digest.
- Developers Agent-native speech memory. Bundled CLI, loopback REST adapter, stdio MCP server.
- Privacy + security Local models, BYOK providers, telemetry policy, permissions, retention.
- Account + license Activation, device management, secure updates, recovery, refunds.
- Troubleshooting Hotkeys, insertion, meeting audio, MCP connect, REST 401, license activation.