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

# Create Your First Mode

> Create your first Superwhisper mode and pick its models along the way. A Message mode works with cloud or local models.

Modes help you customize communication styles across apps and use cases. Every mode includes the voice model that transcribes, and a language model and prompt that shapes the result.

## Create a Message mode

**Message** mode turns your dictation into a ready-to-send message, with a tone slider from casual to formal.

<Steps>
  <Step title="Open Modes">
    Open Superwhisper's settings and click **Modes** in the sidebar.
  </Step>

  <Step title="Create the mode">
    Click **+ Create mode** and select the **Message** preset. Click the mode's name to rename it.
  </Step>

  <Step title="Pick your models">
    Two setups work well:

    <Tabs>
      <Tab title="Cloud (Start here)">
        Keep the defaults: **S1-Voice** for transcription and **S1-Language** for formatting. Nothing to download.

        <img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/do-XBuvOUgvVmZf6/images/screens/mac/modes-editor-cloud.png?fit=max&auto=format&n=do-XBuvOUgvVmZf6&q=85&s=30ee866c5aa9e3b4261b97c7a783c129" alt="Superwhisper Message mode using the S1-Voice and S1-Language cloud models" width="1964" height="1578" data-path="images/screens/mac/modes-editor-cloud.png" />
      </Tab>

      <Tab title="Local">
        Set **Voice Model** to **Cohere Transcribe** and **Language Model** to **S1-mini**. Both run on your device: nothing you dictate leaves it. First use downloads the models (Cohere Transcribe is 1.3 GB).

        <img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/do-XBuvOUgvVmZf6/images/screens/mac/modes-editor-local.png?fit=max&auto=format&n=do-XBuvOUgvVmZf6&q=85&s=8ec2bd55b0e15ccb29944e72e63ceeaa" alt="Superwhisper Message mode running fully on-device with Cohere Transcribe and S1-mini" width="1964" height="1578" data-path="images/screens/mac/modes-editor-local.png" />
      </Tab>
    </Tabs>
  </Step>

  <Step title="Dictate">
    Click into a text field, press **⌥ Space** (Option + Space), and speak. Superwhisper records with your active mode, the one marked with a green dot in the Modes list. Press **⌥ ⇧ K** (Option + Shift + K) to switch modes.
  </Step>
</Steps>

## Explore more models

Open **Settings → Models library** to browse every model, download local ones, and remove ones you no longer use.

<img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/do-XBuvOUgvVmZf6/images/screens/mac/models-library-voice.png?fit=max&auto=format&n=do-XBuvOUgvVmZf6&q=85&s=ba39046c85c18e55a5d9a01f5ea3ea56" alt="Superwhisper Models library listing voice and language models with download options" width="2150" height="1680" data-path="images/screens/mac/models-library-voice.png" />

### Cloud vs. local

|             | Cloud                                     | Local                                           |
| :---------- | :---------------------------------------- | :---------------------------------------------- |
| Setup       | None; works immediately                   | One-time download (75 MB – 3 GB)                |
| Privacy     | Audio processed in the cloud (ZDR policy) | Audio never leaves your device                  |
| Offline use | Requires internet                         | Works offline                                   |
| Speed       | Fast on any hardware                      | Fast on modern hardware                         |
| Best for    | Most users, older machines                | Sensitive work, travel, privacy-conscious users |

### Our picks

| Model                      | Runs  | Size        | Why pick it                                                                                     |
| :------------------------- | :---- | :---------- | :---------------------------------------------------------------------------------------------- |
| **S1-Voice**               | Cloud | No download | The most accurate model we ship (6.6% word error rate)                                          |
| **Cohere Transcribe**      | Local | 1.3 GB      | The most accurate local model (8.4% word error rate); our first pick for on-device              |
| **Parakeet Multilanguage** | Local | 494 MB      | The fastest on Apple silicon, and the only local option for Windows ARM. Best for Multilingual. |
| **Whisper Large v3 Turbo** | Local | 1.6 GB      | The fastest on some Windows machines                                                            |

Numbers come from [our public benchmarks](https://superwhisper.com/benchmarks).

**Every Whisper model is free**, including Whisper Large v3 Turbo. Cohere Transcribe, the Parakeet models, and all cloud models need [Pro](/docs/billing/plans).

**On Windows:** Cohere Transcribe and Whisper Large v3 Turbo run on your GPU through Vulkan, which Windows ARM (Snapdragon) devices don't support yet. On ARM, use Parakeet Multilanguage or a cloud model. Details in [Windows requirements](/docs/get-started/windows#requirements).

For every model's languages, speed, accuracy, and size, see [Voice models](/docs/models/voice) and [Language models](/docs/models/language).

## Next step

<Card title="Understand modes" icon="wand-magic-sparkles" href="/docs/modes/modes">
  Modes decide what happens to your transcription: plain text, a formatted message, an email, or a custom transformation.
</Card>