Hush
A Linux speech-to-text daemon that records audio, transcribes it via the Groq or Fireworks Whisper API, cleans up the text with an LLM, and types the result into whatever window currently has focus.
The intended workflow: bind hush toggle to a global hotkey, press to start recording, press again to stop, and the transcribed text appears in your active application. Use profiles to switch behaviour per hotkey — e.g. one binding for normal dictation, another for translating speech into a shell command.
Requirements
Runtime dependencies:
- pw-record (PipeWire) or
ffmpeg(PulseAudio) — audio capture - wtype (Wayland) or xdotool (X11) — text injection
notify-send— desktop notifications- A Groq or Fireworks API key
Build dependencies:
Installation
sudo ./install.sh
This builds the project, installs the hush binary to /usr/bin/hush, sets up zsh tab-completion, and registers hush.service as a systemd (or OpenRC) user service.
To uninstall:
sudo ./uninstall.sh
Setup
After installing, run the interactive setup wizard to configure your API key and preferences:
hush setup
Config is stored at ~/.config/hush/config in TOML format.
Commands
| Command | Description |
|---|---|
hush toggle |
Start recording if idle, stop and transcribe if recording |
hush start |
Start recording |
hush stop |
Stop recording and transcribe |
hush abort |
Discard the current recording |
hush status |
Show daemon state and recording duration |
hush show |
Show current configuration |
hush latency-test |
Measure STT and LLM round-trip latency |
hush daemon |
Run the daemon in the foreground |
hush setup |
Interactive configuration wizard |
hush profiles list |
List all profiles |
hush profiles get <name> |
Print the contents of a profile |
hush profiles new <name> |
Create a new profile (manual or AI-generated) |
hush profiles edit <name> |
Open a profile in $EDITOR |
hush toggle and hush stop accept a --profile <name> flag to apply a named profile when processing the recording:
hush toggle --profile cmd
Building Manually
./build.sh
Produces a native AOT binary at Hush.Cli/bin/Release/net10.0/linux-x64/publish/Hush.Cli.
Configuration
Key settings in ~/.config/hush/config:
| Key | Default | Description |
|---|---|---|
groq_api_key |
Groq API key | |
fireworks_api_key |
Fireworks API key | |
whisper_provider |
groq |
groq or fireworks |
llm_provider |
groq |
groq or fireworks |
whisper_model |
whisper-large-v3-turbo |
Whisper model to use |
llm_model |
openai/gpt-oss-20b |
LLM model for text cleanup |
audio_backend |
pw-record |
pw-record or ffmpeg |
typing_backend |
wtype |
wtype or xdotool |
whisper_language |
Optional ISO 639-1 language code (e.g. en) |
|
min_recording_duration |
500 |
Minimum recording length in ms |
system_prompt |
Custom LLM system prompt (empty = built-in default) |
Profiles
Profiles let you switch Hush's behaviour on a per-hotkey basis without touching the main config or restarting the daemon. A profile is a partial TOML file stored in ~/.config/hush/profiles/ — only the fields you list override the base config.
Create a profile interactively:
hush profiles new cmd
You will be asked whether to write the prompt manually or have the AI generate it from a description. The profile opens in $EDITOR for final review.
Example profile at ~/.config/hush/profiles/cmd:
whisper_language = "en"
system_prompt = """
Convert the spoken input into a single valid bash command. Output only the raw
command with no explanation, no markdown, and no backticks. If the input is
unclear, output an empty string.
"""
Bind a second hotkey to use it:
Super+R → hush toggle
Super+Shift+R → hush toggle --profile cmd