Hold a key, speak, release -- your words appear wherever your cursor is.

Like SuperWhisper, but free. Like Wispr Flow, but local.

• Cross-platform -- macOS (Apple Silicon) and Linux (Wayland: Sway, Hyprland, etc.)
• Any backend -- local MLX Whisper, any OpenAI-compatible server, whisper.cpp HTTP, or Groq cloud
• Hold-to-record -- global hotkey works in any application
• Free & open source -- no subscription, no cloud dependency required

uv tool install git+https://github.com/jamesob/stt.git

A setup wizard runs on first launch. To update:

uv tool install --reinstall git+https://github.com/jamesob/stt.git

STT checks for missing dependencies at startup and prints install commands. For reference:

Arch Linux:

sudo pacman -S wtype wl-clipboard gtk4-layer-shell \
    gobject-introspection portaudio pipewire-pulse

Debian / Ubuntu:

sudo apt install wtype wl-clipboard gtk4-layer-shell-dev \
    libgirepository1.0-dev gir1.2-gtk-4.0 gir1.2-gtk4layershell-1.0 \
    libportaudio2 portaudio19-dev pipewire-pulse

Your user must be in the input group for keyboard capture:

sudo usermod -aG input $USER
newgrp input  # or log out and back in

Grant Accessibility and Input Monitoring (System Settings > Privacy & Security) to your terminal app -- not to "stt".

stt

Settings live in ~/.config/stt/config.yml. Run stt --config to reconfigure. See config.sample.yml for all options.

language: en
hotkey: cmd_r
sound_enabled: true

backends:
  default:
    provider: openai
    openai_base_url: http://localhost:8000
    openai_whisper_model: whisper-large-v3

order:
  - default

Backends listed in order are tried in sequence. If a backend with connect_timeout is unreachable, STT falls back to the next one:

backends:
  qwen:
    provider: openai
    openai_base_url: http://gpu-server:8200
    openai_whisper_model: Qwen/Qwen3-ASR-1.7B
    connect_timeout: 2
  local:
    provider: mlx
    whisper_model: large-v3-turbo

order:
  - qwen
  - local

Benchmark mode runs all backends in parallel and logs timing for comparison. The first backend in order is the primary (its result is used):

benchmark: true

The prompt setting helps Whisper recognize domain-specific terms:

prompt: Claude, Anthropic, TypeScript, React, API endpoint

git clone https://github.com/jamesob/stt.git
cd stt
uv sync
uv run stt

MIT