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

# Getting started

> A two-minute SpeakoFlow quickstart: grant microphone and accessibility permissions, pick a local speech-to-text model, optionally add a local assistant model, and dictate your first sentence.

[Install SpeakoFlow](/docs/start/install), then run the setup wizard. It takes about two minutes.

<Steps>
  <Step title="Grant permissions" icon="lock">
    The wizard opens with a permissions screen, which it does not count in its own step numbering. The screen skips itself if you have already granted them, and it does not appear on Linux.

    * **Microphone** (macOS and Windows). So SpeakoFlow can hear you.
    * **Accessibility** (macOS only). So it can type into your other apps.

    Skip them and you'll be asked again the next time SpeakoFlow starts. See [Troubleshooting](/docs/reference/troubleshooting) if a permission gets stuck.
  </Step>

  <Step title="Pick a voice model" icon="microphone">
    This is the model that turns your voice into text, and it runs entirely on your machine. A fast English model or a real-time multilingual model are both good starting points.

    The download runs in the background, so you don't wait here. You can switch models anytime in *Settings → Dictation*, and the full catalog is in [Transcription models](/docs/models/transcription-models).
  </Step>

  <Step title="Give it a brain (optional)" icon="brain">
    Download a local model for the assistant and AI cleanup, or choose *Skip for now*. Three Gemma 4 sizes are offered:

    * **Quick** (E2B). Responds fastest, less capable on complex requests.
    * **Balanced** (E4B, recommended). The best conversational quality-to-latency tradeoff.
    * **Capable** (12B). More capable, but noticeably slower.

    You can add or change this later in *Settings → Assistant*, including pointing at a local server or a cloud provider instead. See [Models and providers](/docs/assistant/providers).
  </Step>

  <Step title="You're ready" icon="keyboard">
    The last screen shows your two shortcuts as keycaps, plus a status line for anything still downloading. Your hotkeys are already live.
  </Step>
</Steps>

## Say your first sentence

Open any text field, hold your Dictate shortcut, and talk. Let go, and your words type themselves.

| Action            | Windows                  | macOS                       | Linux                    |
| ----------------- | ------------------------ | --------------------------- | ------------------------ |
| Dictate           | `Left Ctrl` + `Left Win` | `Option` + `Space`          | `Ctrl` + `Space`         |
| Ask the assistant | `Left Ctrl` + `Left Alt` | `Option` + `Ctrl` + `Space` | `Ctrl` + `Alt` + `Space` |

Every shortcut is rebindable in *Settings → General → Shortcuts*.

<AccordionGroup>
  <Accordion title="How the size badges are chosen, and what happens if a download fails">
    The **Quick**, **Balanced**, and **Capable** labels are editorial. They are not inferred from your hardware.

    Tapping a card starts the download and flips the footer straight to *Continue*, so you can move on while it finishes. The built-in assistant provider is only pointed at the model once the weights are actually on disk, so a failed or cancelled download can't leave the assistant set to a model you don't have.
  </Accordion>
</AccordionGroup>

Next: [how SpeakoFlow works](/docs/start/how-it-works).