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

# User guide

> Going over some of the features in Freestyle

## Dictate with the hotkey

Freestyle picks a sensible default hotkey per platform:

| Platform | Default hotkey                                                      |
| -------- | ------------------------------------------------------------------- |
| macOS    | **Fn (Globe)** — the dedicated dictation key, no modifier conflicts |
| Windows  | **Ctrl+Alt+Space**                                                  |
| Linux    | **Ctrl+Alt+Space**                                                  |

Dictation defaults to **Hold (push-to-talk)**. There are two activation modes:

<CardGroup cols={2}>
  <Card title="Hold (push-to-talk)" icon="hand-pointer">
    Hold to record, release to transcribe. Great for quick bursts. This is the default.
  </Card>

  <Card title="Toggle" icon="toggle-on">
    Press once to start, press again to stop. Great for longer dictation.
  </Card>
</CardGroup>

To change it, go to **Settings → Recording**. Pick **Hold** or **Toggle** under **Activation**, and click the current shortcut to rebind it (it needs a modifier key or a side mouse button).

<Note>
  On Linux, true hold-to-talk needs access to the input device. If it isn't available, Freestyle falls back to toggle mode and tells you how to enable it.
</Note>

Under **Output mode** you can choose **Paste into app** (text is typed straight into the active window) or **Copy to clipboard** (you paste it yourself). Clipboard mode helps with apps where auto-paste misbehaves.

<Note>
  On macOS, paste needs **Accessibility** permission. On Linux it uses `xdotool` or `wtype`. If nothing shows up, check **Settings → Permissions**.
</Note>

## Transcription

Freestyle Transcribe is the built-in transcription service, built by the Freestyle team and tuned for developer dictation. Sign in and it works — there is nothing to configure and no API key to paste.

* Transcription and cleanup in one pass, and fast.
* Zero-day retention by default. Transcriptions are private and not stored.

## Shape the final text

Freestyle has four features that turn raw speech into exactly the text you want. Each has its own page with examples and details:

<CardGroup cols={2}>
  <Card title="AI cleanup" icon="sparkles" href="/features/cleanup">
    Run your transcript through a language model to fix punctuation, drop filler, and polish phrasing — at the intensity you choose.
  </Card>

  <Card title="Dictionary" icon="arrow-right-arrow-left" href="/features/dictionary">
    Swap spoken phrases for exact text after transcription, like `type script` → `TypeScript`.
  </Card>

  <Card title="Vocabulary" icon="ear-listen" href="/features/vocabulary">
    Teach the speech model tricky names, brands, and jargon so it spells them right.
  </Card>

  <Card title="Formats" icon="wand-magic-sparkles" href="/features/formats">
    Reshape text based on the app you're in — an email in Gmail, a casual note in Slack.
  </Card>
</CardGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Build a plugin" icon="puzzle-piece" href="/how-plugins-work">
    Extend the dictation pipeline with your own code.
  </Card>

  <Card title="Join the community" icon="discord" href="https://discord.gg/Fmgt5yZCDu">
    Ask questions and hang out with contributors on Discord.
  </Card>
</CardGroup>