> ## 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.

# Intro to Modes

> Superwhisper modes tailor how your voice gets processed, helping you work faster and smarter. Choose the right mode to transform your dictation into exactly what you need.

<img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/CjTilNkn0OPO65M5/images/modes/modes-001.png?fit=max&auto=format&n=CjTilNkn0OPO65M5&q=85&s=7a2ec4a032cafaca28d6d6d330b630bc" alt="Superwhisper's Interface for Modes" width="1724" height="1030" data-path="images/modes/modes-001.png" />

<Tip>For greater workflow flexibility, create different versions of each mode by customizing voice models, AI models, and other settings. **Click any mode's name to rename it.**</Tip>

## Per-Mode Settings

### Voice Processing

After dictating, your audio first goes through voice processing for transcription.

<Steps>
  <Step title="Set your Language">
    * Supported languages vary by voice model
    * Based on your chosen language and voice model, you may see an option to translate your dictation to English. For best results with this option, use Pro, Standard, or Ultra models

    <img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/CjTilNkn0OPO65M5/images/modes/modes-002.png?fit=max&auto=format&n=CjTilNkn0OPO65M5&q=85&s=ef5ce94ce63b0e9e409f2f04bc4f3b6c" alt="Superwhisper's Interface for Language Selection" width="1726" height="1030" data-path="images/modes/modes-002.png" />

    <Note>Your preferred voice model does not support translation to English, or you need translation to another language? Set this up with AI processing by creating a [Custom mode](custom)</Note>
  </Step>

  <Step title="Pick your Voice Model (Cloud or Local)">
    Manage all your models in the Advanced Settings sidebar where you can:

    * Download voice models for local use
    * Connect your own API tokens for supported services
    * Select from the available cloud-based models

    <img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/CjTilNkn0OPO65M5/images/modes/modes-003.png?fit=max&auto=format&n=CjTilNkn0OPO65M5&q=85&s=e5527f37c563b2c280560982e5dff169" alt="Superwhisper's Interface for LLM Selection" width="1486" height="786" data-path="images/modes/modes-003.png" />
  </Step>
</Steps>

***

### Auto-Activation Rules

While in the Advanced Settings sidebar, you can set up rules to automatically switch modes based on your active apps and websites.

<img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/CjTilNkn0OPO65M5/images/modes/modes-004.png?fit=max&auto=format&n=CjTilNkn0OPO65M5&q=85&s=6e4bfccacf3967977a3b2e16b707de7e" alt="Auto-Activation Rules interface for setting up automatic mode switching based on apps and websites" width="1116" height="628" data-path="images/modes/modes-004.png" />

<Note>Keep in mind: Once a mode activates for an app or site, you won't be able to override it, and the system doesn't automatically switch back to your previous mode.</Note>

***

### Advanced Settings

Belo the Auto-Activation Rules, you can select how your audio is handled during dictation.

* **Mute Audio While Recording**
* **Pause Media While Recording**
* **Record from System Audio**
  * Perfect for meetings, video content, interviews, or live audio coming your speakers
  * When recording system audio, the waves on the recording window do not move. You can always check Superwhisper's history to verify capture
* **Identify Speakers**
  * Useful for meeting transcriptions
  * Speaker separation results appear in the Segments tab of History

<Note>Speaker-separated transcripts won't process through AI automatically within the same mode. See [this guide](speaker-separated-meetings) on handling multi-speaker transcripts with AI processing.</Note>

***

### AI Processing

After transcription, AI processing shapes your text based on the mode's purpose.

<img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper/CjTilNkn0OPO65M5/images/modes/modes-005.png?fit=max&auto=format&n=CjTilNkn0OPO65M5&q=85&s=d2f4fc8ff0a670d78e1e9db4ce2a2330" alt="AI Processing settings panel displaying model selection and language processing options" width="1696" height="1000" data-path="images/modes/modes-005.png" />

* Access and manage AI models in the same Advanced Settings sidebar, above the selected voice model
  <Note>Make sure you have selected a mode with AI processing to see this option</Note>
* Built-in modes AI processing support multiple languages automatically
  * Make sure to select your correct language in the [Voice Processing](#voice-processing) settings
  * AI will process your dictation and respond in your chosen language
* AI processing varies by mode
  * [Voice to Text](voice) does not include AI processing
  * [Message](message), [Email](email), [Note](note), [Super](super), and [Meeting](meeting) modes use optimized AI processing instructions to deliver the best results for their specific purposes
  * [Custom Mode](custom) lets you take full control by writing your own AI processing instructions
  * Both [Super](super) and [Custom](custom) modes enhance AI processing capabilities with context awareness, providing additional possibilities

***

## Learn More

<CardGroup>
  <Card title="Switching Modes" icon="arrow-up-arrow-down" href="switching-modes">
    Jump between modes easily with: **Keyboard Shortcuts, Auto-Activation Rules, & Deep Links.**
  </Card>

  <Card title="Customizing Modes" icon="wand-magic-sparkles" href="customizing-modes">
    Want to tweak a built-in mode beyond its basic settings? **Create a Custom Mode to get the exact functionality you need.**
  </Card>
</CardGroup>