> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kombify.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Set up hotkeys, microphone and language

> Change your hotkeys, choose the right microphone and set the speech language

Three settings decide most of what you notice every day: the hotkey that
starts a mode, the microphone SpeechKit listens to, and the language you
speak. All three are in **Settings**.

## Change a hotkey

The defaults are `Ctrl+Win` for Dictation, `Win+Alt` for Assist and
`Ctrl+Shift` for the Voice Agent.

<Steps>
  <Step title="Open the mode">
    In **Settings**, open **Transcribe Mode**, **Assist Mode** or **Voice Agent
    Mode**. The hotkey is on the **Controls** tab.
  </Step>

  <Step title="Pick a base combination">
    Choose one of the presets: `Win+Alt`, `Ctrl+Win` or `Ctrl+Shift`. You can add
    one more key to it: `D`, `J`, `K`, `V` or `Space`.
  </Step>

  <Step title="Or enter your own">
    Choose **Custom…**, type a combination and select **Apply**. A custom combo
    needs at least one modifier plus a key or mouse side button. `Alt+Space` is
    reserved by Windows and cannot be used. Modifier-only combos are allowed
    only for the three presets above.
  </Step>

  <Step title="Choose how it behaves">
    **Hold to talk** records while you hold the keys. **Toggle on press** starts
    on one press and stops on the next.
  </Step>
</Steps>

Each mode needs its own combination. SpeechKit shows a conflict message if two
modes overlap. **Reset** restores the default.

## Choose a microphone

1. Open **Settings > Audio & Speech** and go to **Input**.
2. Under **Audio Input**, choose your microphone from the list.
3. Test with Dictation in a plain text field.

You can also switch the microphone from the quick buttons when you hover over
the overlay. In **Settings > Display & Output** you can choose which quick
buttons appear.

The **Source** choice offers **Microphone** and **System audio**. **Mic +
system** is shown but not selectable yet. System audio is mainly used for
[Meeting](/speechkit/meeting).

## Choose a language

There are two different languages.

**The language you speak.** Open **Settings > Audio & Speech** and go to
**Speech**. Under **Spoken language**, pick a language, **Auto / provider
detect** or **Multilingual (multi)**. The list includes German, English,
Spanish, French, Italian, Portuguese, Dutch, Polish, Swedish, Danish,
Norwegian Bokmål, Finnish, Czech, Ukrainian, Russian, Turkish, Arabic, Hindi,
Japanese, Korean and Chinese. If you switch on **Detect language**, the
provider detects the language itself. Which languages work depends on the
speech model or provider you use.

You can also cycle the speech language from the overlay with **Change
language**, if you added that quick button.

**The language of the app.** Open **Settings > App** and use **Language**. The
default is **System language**. The app is available in English, German,
Spanish, Simplified Chinese, Hindi and Arabic.

## If something goes wrong

* **The hotkey does nothing.** Check that the mode is switched on in
  **Overview** and that the combination does not conflict with another mode.
* **SpeechKit hears the wrong microphone.** Choose the right one under **Audio
  Input**.
* **Words come out in the wrong language.** Set **Spoken language** to your
  language instead of auto detection.
* More help: [Fix common problems](/speechkit/fix-common-problems).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.