Configuration

Configuration

Settings live in ~/.config/agentwhisper/config.toml — created with comments on first run. Restart AgentWhisper after editing (mode, auto-type, and notifications can also be changed live from the tray).

All settings

Section	Key	Default	Meaning
[whisper]	model	base.en	Speech model — see table below
[whisper]	device	cpu	cpu or cuda (NVIDIA GPU with cuDNN)
[whisper]	compute_type	int8	int8 for CPU, float16 for GPU
[hotkey]	key	f12	f1…f12, scroll_lock, pause, insert, menu
[hotkey]	mode	hold	hold = push-to-talk, toggle = press to start/stop
[output]	auto_type	true	Type the text into the active window
[output]	notifications	true	Desktop notification after each dictation
[limits]	max_record_seconds	60	Hard cap on a single recording

Invalid values are rejected at startup with a message listing every problem — AgentWhisper never half-applies a broken config.

Choosing a model

English-only models, best accuracy-per-CPU for dictation:

Model	Download	Speed on a typical CPU	Accuracy
tiny.en	~75 MB	fastest	okay for short phrases
base.en	~140 MB	fast — the default	good
small.en	~460 MB	noticeably slower	very good
medium.en	~1.5 GB	slow without a GPU	best

Models download once into ~/.cache/huggingface/ and are shared with other Whisper tools on your system.

Example

[whisper]
model = "small.en"

[hotkey]
key = "scroll_lock"
mode = "toggle"

[output]
auto_type = false   # clipboard only; paste with Ctrl+V