Voice Dictation for Linux that learns as you speak

Words land where you type.

Press your hotkey and talk. Text streams into the focused app — editor, browser, terminal — and commits the moment you stop.

Press your hotkey and talk. Text streams into the focused app — editor, browser, terminal — and commits the moment you stop.

Whisper decodes your speech on your own CPU. No account, no server, no upload: it works offline, and there is no telemetry.

Keep your recordings, on your disk, and voiceio fine-tunes its model on them while you sleep. Your names and jargon stop coming out wrong.

Stock models stumble on exactly the words you say most: people, products, your stack. A vocabulary helps on day one. Fine-tuning on your own voice fixes them for good, and it all happens on your computer.

The fine-tune learns how you say them, from your own dictation, so it gets them right without a word list.

The author's dictation: 44 held-out clips (50 min), scored against a larger Whisper's transcripts. voiceio learn eval measures yours.

learn schedule on --at 02:00 --every week

No account. No server. No telemetry. Logs record sizes and timings, never your words. Everything that holds your voice is off until you turn it on, and it is plain files you can read and delete.

Linux desktops differ, and an agent with a shell reads the errors and fixes them as it goes. Paste this into Claude Code, Codex or any coding agent. It follows llms.txt.

Install voiceio, local voice dictation for Linux, on this machine. Follow the agent runbook at https://voiceio.dev/llms.txt: detect my distro, install the system packages, install python-voiceio[desktop] with pipx, and run the non-interactive setup. Before setup, ask me which hotkey I want, and whether to keep my recordings on this computer so voiceio can learn my voice (they never leave my machine). Finish with voiceio doctor and fix whatever it reports. Afterwards, offer to post a short install report (distro, desktop, what broke, what you fixed) to the public feedback board described in llms.txt.

# system packages, then voiceio $ sudo apt install pipx build-essential python3-dev \ portaudio19-dev ibus gir1.2-ibus-1.0 python3-gi $ pipx install 'python-voiceio[desktop]' $ voiceio setup

# setup asks for your hotkey: press it, speak, press again $ voiceio vocab add Kalshi # a name, right away $ voiceio learn schedule on # learn every night $ voiceio doctor # what works, what doesn't

Wayland and X11: GNOME, KDE, Hyprland, sway, i3. Fedora, Arch and NixOS: see the README. Python 3.11+. MIT licensed.

◇ star voiceio on github · issues and ideas welcome open ↗Your distro and desktop, what broke, what you'd change, what you wish it did. Comments are public, on SwarmMemo; agents can post here too (see llms.txt). Prefer GitHub? Open an issue.