# Failed Appstore Activation
Source: https://superwhisper.com/docs/common-issues/appstore

How to Fix failed Appstore Activation.

## Restoring Your SuperWhisper Subscription

This guide applies only to users who purchased a SuperWhisper Subscription through the App Store on an iOS device.

Occasionally, the App Store may fail to properly activate your SuperWhisper iOS app. Follow these steps to resolve the issue:

<Steps>
  <Step title="Open the App's Settings">
    Launch SuperWhisper on your iPhone and tap the gear icon located in the top-right corner of the screen.
  </Step>

  <Step title="Access your License Settings">
    Navigate to the "SuperWhisper Pro" tab and tap to open it.
  </Step>

  <Step title="Recover your License">
    Tap the "Recover my License Key" button. This should reactivate your subscription.
  </Step>
</Steps>

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/appstore.png" alt="Desktop QR Code Activation Screen" />


# Hallucinations and Silence Removal
Source: https://superwhisper.com/docs/common-issues/hallucinations



## What's the issue?

If you are noticing hallucinations or repetition at the end of your transcription, this is likely due to long periods of silence in your recorded audio.

## How to Fix it

To fix this, we are going to enable the Silence Removal feature.

First open the "Configuration" tab on the left.

Then enable "Advanced Settings." This will show you some new options.

Scroll down and enable the "Silence removal" option.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/Silence-removal.png" />

This should help with the hallucinations and repetition.


# Realtime Unavailable
Source: https://superwhisper.com/docs/common-issues/realtime



## What's the issue?

The reason Realtime is grayed out is because it is only supported buy the Nova (Cloud) Voice model.

## How to Fix it

To enable Nova (Cloud), open Superwhisper settings and navigate to Voice model/Model and pick Nova (Cloud) from the drop down.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/realtime-1.png" />

You can then enable the Realtime feature via the slider.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/realtime-2.png" />

Hope this page helped solve your issue. Cheers.


# Unable to Create Modes
Source: https://superwhisper.com/docs/common-issues/unable-to-create-mode



## What's the issue?

Sometimes when enabling ICloud Documents syncing, the Superwhisper folder moves to ICloud, but Superwhisper still thinks its in documents.

This causes Superwhisper to not be able to do things like create modes.

## How to Fix it

To fix this, we are going simply reselect documents as the folder location.

First open the "Configuration" tab on the left.

Then enable "Advanced Settings." This will show you some new options.

Scroll down and Click the "change folder" option.

Navigate to your Documents folder and click "open".

Now all you need to do is click "confirm" and you should be good to go!

<AccordionGroup>
  <Accordion title="Enable Adv Settings">
    <Frame>
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/unable-to-create-mode-1.png" alt="Enable Adv Settings" />
    </Frame>
  </Accordion>

  <Accordion title="Change Folder">
    <Frame>
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/unable-to-create-mode-2.png" alt="Change Folder" />
    </Frame>
  </Accordion>

  <Accordion title="Navigate to Documents">
    <Frame>
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/unable-to-create-mode-3.png" alt="Navigate to Documents" />
    </Frame>
  </Accordion>

  <Accordion title="Change Confirmation">
    <Frame>
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/common-issues/unable-to-create-mode-4.png" alt="Change Confirmation" />
    </Frame>
  </Accordion>
</AccordionGroup>

Hope this helped solve your issue and have a great rest of your day!


# iOS App Activation
Source: https://superwhisper.com/docs/get-started/activate-ios

Extend Superwhisper's powerful dictation capabilities to your mobile device with the iOS app.

## Step-by-Step

<Steps>
  <Step title="Download the App">
    Get Superwhisper for iOS from the [App Store](https://apps.apple.com/us/app/superwhisper/id6471464415).
  </Step>

  <Step title="Access your License Settings">
    Once installed, open the iOS app and navigate to Settings. Look for the "superwhisper PRO" option, which allows you to activate your license on your mobile device.

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/activate-ios-001.png" alt="Desktop QR Code Activation Screen" />
  </Step>

  <Step title="License Activation">
    To complete activation, you'll need to scan a QR code from your desktop app:

    1. On your desktop app, go to Settings > License
    2. Locate the mobile activation QR code
    3. Use your iOS device to scan the displayed code

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/activate-ios-002.png" alt="Desktop QR Code Activation Screen" />
  </Step>
</Steps>

***

## Troubleshooting

**Having trouble with the QR code? Here's a simple fix:**

1. Open the QR code screen on your Mac
2. Double-click your license key (you'll see "Copied to clipboard")
3. Create the activation link:
   * Start with: `superwhisper://license/`
   * Paste your key after the slash
   * Example: `superwhisper://license/XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX`
4. Open this link on your iOS device

This manual activation method works just as well as the QR code scan.

**Bought it though the app store and it wont activate?**

You can follow this guide to fix this issue [Here](https://superwhisper.mintlify.app/common-issues/appstore).


# MacOS App Activation
Source: https://superwhisper.com/docs/get-started/activate-mac

How to activate the MacOS app Via an iOS App Store Subscription.

## Step-by-Step

<Steps>
  <Step title="Download the App">
    Get Superwhisper for MacOS from [Our Website](https://superwhisper.com/).
  </Step>

  <Step title="Access your License Settings">
    Once installed, open the MacOS app and navigate to [Settings](https://superwhisper.mintlify.app/get-started/settings). Look for the "License" tab.

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/activate-mac-001.png" alt="Desktop Pro Activation Screen" />
  </Step>

  <Step title="License Activation">
    To complete activation, you'll need to copy the key from your iOS app.

    1. On your iOS app, go to Settings > "Superwhisper Pro"
    2. Locate the "Reveal License Key"
    3. Tap it to reveal your key
    4. You can then type this into the "License Key" Box on the MacOS app. Be sure to keep the upper case lettering.

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/activate-mac-002.png" alt="Desktop QR Code Activation Screen" />

    If your iOS app is failing to activate you can follow this [Guide](https://superwhisper.mintlify.app/common-issues/appstore) to fix it.
  </Step>
</Steps>


# Introduction
Source: https://superwhisper.com/docs/get-started/introduction

Superwhisper: ultra-fast AI powered dictation that understands what you want to say and how you want to say it.

<img style={{ borderRadius: '0.5rem' }} noZoom src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/hero-dark.png" alt="Superwhisper Interface" />

Instantly turn speech into perfect emails, crisp notes, clear messages, professional communication, and more.

## How It Works

<Steps>
  <Step title="Dictation">
    Just talk as you normally would.
  </Step>

  <Step title="Transcription">
    AI converts your speech into text with exceptional accuracy.
  </Step>

  <Step title="Smart Processing">
    AI transforms your transcription to match exactly what you need.
  </Step>
</Steps>

***

## Key Features

<AccordionGroup>
  <Accordion title="Intelligent Modes">
    Choose from built-in modes such as pure voice transcription, tailored text formatting, or create your own custom modes with personalized AI instructions. Each mode processes your dictation differently - from simple voice-to-text to complex transformations that match your exact requirements and workflow preferences.
  </Accordion>

  <Accordion title="Context-Aware AI">
    When enabled, Superwhisper's context awareness understands your specific needs and delivers smarter, more personalized results.
  </Accordion>

  <Accordion title="File Transcription">
    Aside from dictation, Superwhisper can transform existing audio and video files into text. Perfect for processing lectures, meetings, or interviews.
  </Accordion>

  <Accordion title="Language Support">
    Dictate in your preferred language and translate to English on the fly, use built-in modes in your language, or create custom modes to harness Superwhisper's capabilities across 100+ supported languages.
  </Accordion>

  <Accordion title="Use Your Own API Keys">
    Superwhisper's flexibility extends beyond our built-in models. Integrate your own API keys to access additional AI providers and models, expanding your capabilities even further.
  </Accordion>

  <Accordion title="Unlimited AI">
    Experience unlimited access to powerful cloud & local AI models including OpenAI GPT-4o, Anthropic Claude 3.5 Sonnet, Deepgram Nova 2, Groq Llama 3.1, and more. Process dictations with state-of-the-art language models without worrying about usage limits or additional costs.
  </Accordion>
</AccordionGroup>

<Note>
  New users receive 15 minutes of free access to all pro features and the ability to create 3 modes to experience Superwhisper's full potential.
</Note>

***

## Initial Setup

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/introduction-001.png" alt="Superwhisper Onboarding" />

**When you first launch Superwhisper, the onboarding process will help you:**

* Set up essential system permissions for dictation
* Choose your preferred language for transcription
* Select your AI model (cloud or local) with system-optimized suggestions
* Configure your microphone and audio settings
* Complete a guided first dictation with keyboard shortcuts
* Test and verify your setup is working correctly

**By the end of onboarding, you'll have completed the basic setup. To fine-tune Superwhisper for your specific needs, just click the menu bar icon to access all settings anytime.**

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/introduction-002.png" alt="Superwhisper Settings Menu" />

***

## Explore More

<CardGroup cols={2}>
  <Card title="All About Modes" icon="wand-magic-sparkles" href="/modes">
    Discover how to leverage different modes for maximum productivity
  </Card>

  <Card title="Transcribing Files" icon="desktop" href="transcribe-history">
    Need to use Superwhisper on files? Check this guide on file transcription methods
  </Card>

  <Card title="Troubleshooting" icon="wrench" href="../common-issues/realtime">
    Find solutions to common questions
  </Card>

  <Card title="Report an Issue" icon="bug" href="report">
    Help us improve by reporting any problems you encounter
  </Card>
</CardGroup>

<Info>
  Your license covers both desktop and iOS versions - giving you powerful AI dictation capabilities across all your devices at no additional cost. [Learn how to activate Superwhisper on iOS.](activate-ios)
</Info>


# Report an Issue
Source: https://superwhisper.com/docs/get-started/report

Learn how to get help when Superwhisper isn't working as expected

## Overview

This guide outlines the essential information needed to report issues effectively, ensuring quick and accurate solutions for any challenges you encounter with Superwhisper.

<Info>
  For quick support, reach out at [support@superwhisper.com](mailto:support@superwhisper.com). You can also share your issue in [Superwhisper's Discord server](https://discord.gg/tF98XvJNvB), under the appropriate channel. While our Discord community often provide helpful advice, email support typically offers the fastest path to resolving your issue.
</Info>

## Enable Error Reporting

<Steps>
  <Step title="Access Configuration">
    Navigate to the configuration page in Superwhisper settings
  </Step>

  <Step title="Enable Error Logging">
    Locate and enable the error log toggle switch

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-001.png" alt="Superwhisper Error Logging" />
  </Step>
</Steps>

## Reporting Through History

The most effective way to report issues related to recordings, is directly through Superwhisper's history.

<Steps>
  <Step title="Access History">
    Click the menu icon in Superwhisper and select "History"

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-002.png" alt="Access Superwhisper History" />
  </Step>

  <Step title="Submit Your Recording">
    Find the problematic recording in the left sidebar and right-click to select "Report Issue"

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-003.png" alt="Report Issue from Superwhisper History" />
  </Step>
</Steps>

## Manual Reporting via Email

As an alternative method you can submit issues manually via email. Here's what to include:

### Required Screenshots

<AccordionGroup>
  <Accordion title="Main Superwhisper Configuration">
    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-004.png" alt="Superwhisper Main Configuration" />
  </Accordion>

  <Accordion title="Active Mode Settings">
    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-005.png" alt="Superwhisper Mode Settings" />
  </Accordion>

  <Accordion title="Custom Mode Prompt Configuration">
    If you're using a Custom Mode, include a screenshot of your prompt configuration

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-006.png" alt="Superwhisper Custom Mode Configuration" />
  </Accordion>
</AccordionGroup>

### Collecting Test Recording Data

<Steps>
  <Step title="Create Test Recording">
    Make a brief recording demonstrating the issue
  </Step>

  <Step title="Access History">
    From within the history panel, select the test recording and reveal its folder in Finder

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-007.png" alt="Reveal Recording in Finder" />
  </Step>

  <Step title="Compress and Send">
    Compress the selected folder and attach it to your email along with the screenshots

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/report-008.png" alt="Compress Recording Files" />
  </Step>
</Steps>

***

<Note>
  Whichever method you choose, remember to provide a clear description of the issue and include any steps necessary to reproduce the problem.
</Note>


# Open Settings
Source: https://superwhisper.com/docs/get-started/settings

How to Open Settings.

There are two ways to open settings.

<Steps>
  <Step title="Open via the toolbar.">
    Up in your toolbar near the wifi symbol, there should be a Superwhisper Logo.

    When you click on it, a list of options should appear.

    Go down to settings and click to open. Just like that, settings should be open!

    <video style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/videos/get-started/settings-1.mp4" controls width="100%" height="auto" />
  </Step>

  <Step title="Open it via keybind">
    When you have the SuperWhisper dictation window open, click on the window to engage it and press the ⌘ and , keys to open settings.

    This should then open the settings window!

    <video style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/videos/get-started/settings-2.mp4" controls width="100%" height="auto" />

    Have a great day!
  </Step>
</Steps>


# Advanced Settings
Source: https://superwhisper.com/docs/get-started/settings-advanced

Superwhisper's advanced configuration options let you modify application behavior, adjust performance settings, and manage system-level preferences for a personalized dictation experience

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-advanced-001.png" alt="Superwhisper Advanced Settings" />

Superwhisper's advanced configuration options let you modify application behavior, adjust performance settings, and manage system-level preferences for a personalized dictation experience.

***

## Interface Customization

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-advanced-002.png" alt="Superwhisper Interface Options" />

### Show in Dock

Control whether Superwhisper appears in your dock for quick access

### Start Recording on Menubar Click

Enabling this toggle will allow you to start or stop your recording by clicking on the menu icon. If you want to access the regular options from the menu bar icon, you will just simply right click on it.

### Recording Window Enabled

If you prefer to stay focused on your work without visual distractions, you can disable the recording window. Audio cues will still notify you when recording starts and when processing completes.

### Auto-Close Window

By default, with recording window and paste result enabled, the window closes only after successful paste detection. Enable this setting to automatically close the Recording Window after every dictation, regardless of paste status. Your dictated text remains in the clipboard for manual pasting if needed.

***

## Voice Processing Options

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-advanced-003.png" alt="Superwhisper Voice Processing Options" />

### Voice Model Active Duration

Adjust the active duration of voice processing to balance between speed and resource usage. Higher durations keep the AI model loaded in system memory, enabling faster initial processing but reducing available resources for other applications. Lower durations free up system memory but may require additional time when starting new dictation sessions.

### Silence Removal

Silence removal helps you get better transcripts and faster results by skipping quiet parts in your audio. Additionally, this feature is helpful in the prevention of AI hallucinations during silent moments. If you see text you never said in your transcripts, turning on silence removal may fix this by stopping the AI from trying to make sense of silence.

***

## Folder Location

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-advanced-004.png" alt="Superwhisper Folder Location" />

Superwhisper keeps configuration files in your Documents folder by default. This folder stores your history files, your custom modes settings, vocabulary, and text replacements. **Creating a backup of this folder is recommended if you want to preserve your personalized configurations or transfer them to a new machine.**

<Note>
  Since Superwhisper actively uses this folder during dictation, ensure it remains locally accessible on your device. If using iCloud sync for your Documents folder, verify that this specific folder remains local to prevent operational issues.
</Note>

***

## Text Processing Controls

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-advanced-005.png" alt="Superwhisper Text Processing Options" />

### Paste Result Text

This toggle works in conjunction with the recording window settings to determine how Superwhisper delivers transcription results. Keep in mind that if you disable both the recording window and paste result options, Superwhisper will still save the results to your clipboard - you'll just need to paste it manually since you won't see the text on screen.

### Hold Shift to Auto-Send

With this option enabled, holding the shift key when you finish your dictation automatically simulates pressing the return/enter key. This feature is particularly useful for quick messages in chat applications or cases where immediate action is desired.

### Restore Clipboard

By default, your results will replace whatever was on your clipboard before dictating. When you turn on this toggle, Superwhisper will put your previous clipboard content back exactly as it was.

### Simulate Keypresses

This option provides an alternative input method for applications where direct paste operations aren't possible due to system privacy settings or application restrictions. When enabled, Superwhisper simulates individual keystrokes to input your results.


# Overview
Source: https://superwhisper.com/docs/get-started/settings-overview

Learn how to personalize Superwhisper's settings and options to enhance your voice-to-text experience and maximize productivity

**Superwhisper is designed to work excellently right out of the box, so if you've completed the initial onboarding, you're already set to start dictating.** While the default configuration suits most users perfectly, one of Superwhisper's greatest strengths is its customization potential.

Superwhisper offers a wide range of customization options to help you create the perfect dictation environment. From basic audio settings to advanced configuration options, you can tailor the application to match your specific needs and workflow preferences.

***

## Configuration Areas

<CardGroup cols={2}>
  <Card title="Sound" icon="volume-high" href="settings-sound">
    Adjust your microphone and sound settings for effective voice capture
  </Card>

  <Card title="Keyboard Shortcuts" icon="keyboard" href="settings-shortcuts">
    Set your preferred keyboard shortcuts for a smooth, effortless dictation
  </Card>
</CardGroup>

<Card title="Advanced Settings" icon="sliders" href="settings-advanced">
  Take control of how Superwhisper works. Customize the behavior of your recording window, tweak settings to boost performance, and discover more settings to unlock Superwhisper's full potential for your workflow
</Card>


# Keyboard Shortcuts
Source: https://superwhisper.com/docs/get-started/settings-shortcuts

Customize your keyboard shortcuts to control your dictation efficiently and enhance your productivity with quick commands

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-shortcuts.png" alt="Superwhisper Keyboard Shortcuts" />

Access the Keyboard Shortcuts section in Superwhisper's Configuration tab. Each shortcut can be modified to avoid conflicts with other applications and create a workflow that feels natural to you.

***

## Toggle Recording

Set up a keyboard combination to start and stop your recordings. Single modifier keys (like Left Command, Right Command, or Fn key) can be used independently, providing additional flexibility in your shortcut configuration.

***

## Cancel Recording

This command allows you to cancel an active recording:

* For recordings under 30 seconds: Cancels immediately
* For longer recordings: Shows a confirmation prompt to prevent accidental cancellations

<Note>
  After completing your recording, your dictation enters the processing stage. During this time, using the cancel shortcut will only hide the recording window.
</Note>

***

## Change Mode

This keyboard shortcut allows you to switch between different modes:

* Hold your chosen modifier key and tap the assigned key to cycle through modes
* Only works when the recording window is active
* Make sure to select your mode before starting dictation

***

## Push-to-Talk

Enables precise control over your recording sessions:

* Press and hold to record
* Release to stop recording
* Can share the same shortcut as Toggle Recording

<Info>
  If you're setting up a shared shortcut for Push-to-Talk and Toggle Recording, try pressing the main key before adding modifier keys if you encounter configuration issues.
</Info>

***

## Explore More

<Card title="Beyond Shortcuts" icon="wand-magic-sparkles" href="../modes/switching-modes">
  Discover more ways to switch modes in Superwhisper. Use auto-activation rules, deep links, or automation tools - ideal for power users looking to enhance their workflow.
</Card>


# Sound
Source: https://superwhisper.com/docs/get-started/settings-sound

Configure your audio settings for optimal dictation performance

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/settings-sound.png" alt="Superwhisper Sound Configuration" />

## Input Device

Your dictation quality depends on having the right audio settings. Superwhisper's sound configuration lets you pick your microphone, set optimal volume levels, and customize how it works on your particular audio setup.

<Steps>
  <Step title="Select Input Device">
    Choose your preferred audio input or let Superwhisper automatically select based on system defaults. The automatic option ensures Superwhisper always uses your system's primary input device.
  </Step>

  <Step title="Adjust Microphone Volume">
    Enable automatic volume adjustment (recommended) to set your microphone's input level for clear voice recordings. This ensures your voice is captured at the right volume without manual adjustments.
  </Step>

  <Step title="Audio Engine Selection">
    Not all microphones or devices are compatible with the new audio engine. If you experience audio capture issues, try disabling this option before reporting an issue.
  </Step>
</Steps>

<Tip>
  Want faster processing and better results with your transcription? Check out the silence removal setting in Advanced Configuration.
</Tip>

***

## Sound Effects

**Superwhisper includes customizable audio feedback to enhance your dictation experience.** These subtle cues help you stay informed about the application's status without needing to watch the screen. You can adjust the volume of sound effects independently from your system volume, or disable them completely if you prefer silent operation.

<CardGroup cols={2}>
  <Card title="Recording Indicator" icon="microphone" horizontal>
    A quick audio cue lets you know when your dictation can begin
  </Card>

  <Card title="Processing Completion" icon="check" horizontal>
    A brief tone signals when your dictation has been processed
  </Card>
</CardGroup>


# How to Transcribe from History or from a File
Source: https://superwhisper.com/docs/get-started/transcribe-history



## Why Transcribe from History?

Transcribing from history offers several advantages.

If a file fails to transcribe or the app crashes, you can still use the recording to generate your text output.

Additionally, you might want to transcribe from history if you wish to adjust the mode settings or switch to an entirely different mode.

## How to Transcribe from History

Open the app settings window, and click the History tab on the left.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/transcribe-history-1.png" />

In History, right-click on any recording you want to re-transcribe and select "Process again."

If you want to try something different with your audio recording, you can use a different mode.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/transcribe-history-2.png" />

## How to Transcribe a File

To transcribe an audio file from your computer, first go to your toolbar and click "Transcribe file..."

This icon appears in the toolbar, located in the top-right corner of your Mac screen, alongside the Wi-Fi indicator and clock.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/transcribe-history-3.png" />

This will open a window where you can select your audio file.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/get-started/transcribe-history-4.png" />

These simple steps allow you to re-transcribe from history or transcribe any audio file with ease!


# Custom
Source: https://superwhisper.com/docs/modes/custom

Take full control of your dictation processing with Custom Mode. Create specialized workflows by combining context-awareness with your own AI instructions for unlimited possibilities.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-custom-001.png" />

## Key Features

**Custom Mode empowers you with:**

* Complete control over AI processing instructions
* Context-awareness capabilities
* Advanced audio capture options
* Flexible processing for any workflow

***

## Additional Settings

### AI Instructions

Beyond selecting your preferred AI model, with Custom Mode you have the option to personalize your own AI processing instructions.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-custom-002.png" />

<Note>Instructions are empty by default. Select "Change Prompt" to modify them. If left blank, AI will not know what task to perform and may give unexpected results. </Note>

### Audio Options

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-custom-003.png" />

* **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>

### Context Awareness

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-custom-004.png" />

Inside the Change Prompt section, you'll discover two powerful features:

* Use application context toggle
* Use copied text toggle

<Note>These toggles work identically to [Super Mode context awareness features](super#context-awareness).</Note>

***

## Prompting Tips

<AccordionGroup>
  <Accordion title="Referencing Content">
    **When writing AI instructions for use in Superwhisper, you can direct AI's attention to specific content using these XML-style tags:**

    * `<user_message>`
      * Contains your dictated text
    * `<application_context>`
      * Includes the data from your active application window
    * `<clipboard_context>`
      * Contains the text you've copied

    ***

    T**hese tags let you create targeted instructions for AI**. For example:

    * "Translate `<user_message>` to Spanish"
    * "Based on `<application_context>`, suggest relevant code comments"
    * "Format `<user_message>` accordingly based on the content found in `<clipboard_context>`"

    <Tip>If you want AI to know your input is dictated speech, include it explicitly. For example: *"The `<user_message>` contains dictated text. Please format it into proper paragraphs."*</Tip>

    ***

    **Instruct AI exactly which content to focus on and what to do with it.** You can combine them in your instructions to create powerful workflows:

    ```
    If <application_context> shows a code editor:
    - Format <user_message> as code comments
    - Use coding style from <clipboard_context> as reference
    ```
  </Accordion>

  <Accordion title="Writing Effective Instructions">
    <Steps>
      <Step title="Clear Purpose">
        Define your AI instructions by starting with a clear role or purpose statement. This sets the foundation for how the AI will process your content.
      </Step>

      <Step title="Requirements">
        Create a detailed list of specific requirements and expectations. Being explicit helps ensure the AI understands exactly what you need.
      </Step>

      <Step title="Structure">
        Organize your instructions using separate sections for different components. This modular approach makes your instructions easier to understand and modify.
      </Step>

      <Step title="Keep Simple">
        Write direct, straightforward instructions without unnecessary complexity. Clear communication leads to better results.
      </Step>
    </Steps>
  </Accordion>

  <Accordion title="Using XML Tags">
    **It is suggested to structure your instructions with XML tags to communicate clearly with AI:**

    **Basic Tag Structure**

    * Set a role and Instructions:

    ```xml
    <role>You are a text editor</role>
    <instructions>Format the content of `<user_message>` into clear paragraphs</instructions>
    ```

    * Define specific requirements:

    ```xml
    <requirements>
    - Use simple, clear language
    - Keep the casual tone
    - Break into short paragraphs
    </requirements>
    ```

    * Provide context and style:

    ```xml
    <context>
    - This content is for a cooking blog post
    - Target audience is home cooks
    - Should use casual, approachable language
    - Include cooking-specific terminology where relevant
    </context>

    <style>
    - Write in a warm, encouraging tone
    - Use descriptive but simple language
    - Include helpful cooking tips
    - Make instructions easy to follow
    </style>

    <output-format>
    - Title and introduction
    - Ingredient list
    - Step-by-step instructions
    - Cook's notes and tips
    </output-format>
    ```

    <Note>Adjust and expand your XML tags based on your specific needs. The more detailed your instructions, the better the results.</Note>
  </Accordion>

  <Accordion title="Add Examples">
    **Examples help you teach AI exactly how to process your input and what kind of output you expect.** Located at the bottom of the Change Prompt section, below the context toggles, you'll find the Add Examples interface.

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-custom-005.png" />

    **Each example consists of two parts:**

    * Input field: Shows how you'll phrase your requests
    * Output field: Demonstrates your expected AI response

    **How to set:**

    * Click "Add Example" to create your first example pair
    * Fill in both the input and output fields
    * Add more examples by clicking "Add Example" again
    * Right-click any example to duplicate or delete it

    <Note>Adding 2-3 examples significantly improves AI's understanding of your needs and leads to more accurate responses.</Note>
  </Accordion>
</AccordionGroup>

***

## Advanced Tip

Currently, Custom Mode doesn't include text selection context like [Super Mode](super). Enable this by editing your mode's JSON config file - just back up first and use a simple text editor like TextEdit or VS Code.

<CardGroup cols={2}>
  <Card title="Locate Your Modes Folder" icon="circle-1">
    Open Finder and navigate to \~/Documents/SuperWhisper/modes/ to access your modes folder
  </Card>

  <Card title="Find Your Mode File" icon="circle-2">
    Use Quick Look (press Space) on JSON files to preview and identify your mode by its "name" field
  </Card>

  <Card title="Enable Selection Context" icon="circle-3">
    Open the JSON file and change "context\_from\_selection" from `false` to `true`
  </Card>

  <Card title="Restart to Apply" icon="circle-4">
    Save your changes and restart Superwhisper to activate the selection context feature
  </Card>
</CardGroup>

<Icon icon="check" iconType="solid" /> *Awesome! You can now reference `<text_selection_context>` in your custom instructions, as covered in [Prompting Tips](#prompting-tips).*

***

<Tip>Unlike other modes, Custom Mode isn't limited to text formatting. **Combine context-awareness with your instructions to create powerful, specialized workflows tailored to your needs.**</Tip>


# Customizing Built-In Modes
Source: https://superwhisper.com/docs/modes/customizing-modes

Want to tweak a built-in mode? Learn how to create customized versions of your favorite modes by accessing their AI instructions and adding your own adjustments—perfect for when you need something between built-in and fully custom.

<Note>This guide covers a more advanced workflow that requires basic understanding of AI prompting and Superwhisper's features. If you're new to Superwhisper, start with the built-in modes first.</Note>

## Overview

Built-in modes are regularly updated based on user feedback to cover common use cases. **To customize a built-in mode, you will essentially need to copy its AI instructions to create a new [Custom Mode](custom) with this.** While your customized version won't receive AI instruction updates when enhancements are published for the original mode, it's still a great way to create something tailored to your needs without starting from scratch.

## Step-by-Step

<Steps>
  <Step title="Create a Test Recording">
    1. Create a new mode using the built-in mode you want to customize
    2. Make a quick test recording (a simple "This is a test" works fine)
    3. Let it process through AI
  </Step>

  <Step title="Access the Original Instructions">
    1. Open the History tab
    2. Find your test recording
    3. Look for the prompt box in the bottom right sidebar
    4. Select and copy all text
    5. Paste into a text editor for better visibility

    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-customizing-001.png" />
  </Step>

  <Step title="Extract What You Need">
    1. Find the `<instructions>` XML tags
    2. Copy only the content between these tags
    3. If present, note any `<examples>` sections
  </Step>

  <Step title="Create Your Custom Version">
    1. Create a new Custom Mode
    2. Click "Change Prompt"
    3. Paste the copied instructions
    4. Add any examples from the original mode
    5. Make your desired adjustments
  </Step>
</Steps>

<Tip>Not sure what to customize? From context awareness to capturing system audio, check out [Custom Mode](custom) to explore all the powerful features you can add to your workflow.</Tip>


# Email
Source: https://superwhisper.com/docs/modes/email

Transform your spoken words into properly formatted emails instantly - just speak naturally and let Email Mode handle the structure.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-email-001.png" />

## Key Features

**This mode makes email dictation effortless by:**

* Adding smart greetings and closings
* Keeping your natural tone and style
* Highlighting key action items
* Fixing grammar and punctuation

***

<Check>Email Mode takes your natural speech and adds proper email structure while keeping your authentic voice.</Check>


# Meeting
Source: https://superwhisper.com/docs/modes/meeting

Meeting mode records audio from your meetings and transcribes it into a clear summary, helping you capture key points without the noise.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-meeting-001.png" />

## Key Features

**Meeting Mode streamlines your meetings by:**

* Converting spoken discussions into concise summaries
* Preserves important context while removing redundant content

<br />

<Check>Perfect for team meetings, client calls, and any conversation you need to review later.</Check>

***

## Advanced Tip

<Card title="Speaker-Separated Meetings" icon="users" href="speaker-separated-meetings">
  Want to separate different speakers in your meeting transcripts? Explore how Custom Mode can be used to handle speaker recognition for advanced AI processing. With Superwhisper it is possible to track who said what.
</Card>


# Message
Source: https://superwhisper.com/docs/modes/message

Message Mode enhances your dictation with smart formatting and grammar fixes, delivering polished, ready-to-send messages that capture your voice while maintaining clarity.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-message-001.png" />

## Key Features

**Message Mode takes your dictation beyond basic transcription by:**

* Removing speech artifacts and filler words
* Fixing grammar and punctuation
* Formatting text for readability
* Maintaining natural conversation flow

***

<Check>Unlike the basic transcription in Voice Mode, Message Mode applies AI processing to your dictation. **It intelligently refines your speech while preserving your voice and communication style.**</Check>


# Intro to Modes
Source: https://superwhisper.com/docs/modes/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://mintlify.s3.us-west-1.amazonaws.com/superwhisper/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.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-002.png" />

<Steps>
  <Step title="Pick your Model (Cloud or Local)">
    Manage all your models in the AI Models tab where you can:

    * Use cloud-based models
    * Download voice models for local use
    * Connect your own API tokens for supported services
  </Step>

  <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, use Pro, Standard, or Ultra models
      <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="Control Audio">
    Mute & pause recording automatically when dictating with the current mode
  </Step>

  <Step title="Real-time Processing">
    * Real-time transcription is available when using the Nova (Cloud) model
    * Toggle this option to see your words appear in the recording window instantly as you speak
  </Step>
</Steps>

***

### AI Processing

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

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-003.png" />

* Access and manage AI models through the dedicated tab
* 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 Mode](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

***

### Auto-Activation Rules

Set up rules to automatically switch modes based on your active apps and websites.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/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>

***

## 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>


# Note
Source: https://superwhisper.com/docs/modes/note

Turn your spoken ideas into structured, easy-to-read notes. Notes Mode helps you capture and organize your thoughts with smart formatting and clear hierarchies.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-note-001.png" />

## Key Features

**Notes Mode transforms your spoken words by:**

* Improving clarity
* Formatting text for optimal readability
* Highlighting key points and action items
* Adapting content structure based on topic and key topics
* Creating lists or bullet points from your dictation

***

<Check>Note Mode is perfect for lectures, meetings, brainstorming sessions, and quick thought capture.</Check>


# Speaker-Separated Meetings
Source: https://superwhisper.com/docs/modes/speaker-separated-meetings

Learn how to transcribe meetings with speaker separation and process them with AI for enhanced insights. This method combines Superwhisper's speaker identification capabilities with powerful AI processing.

<Note>
  This is an advanced workflow requiring configuration file edits and multiple steps. If you need basic meeting summaries, consider using the standard Meeting Mode.  Or, if you want speaker-separated transcripts with basic AI processing, simply enable speaker separation in a Custom Mode with Nova (Cloud) for voice.
</Note>

## Overview

This guide shows you how to combine speaker-separated transcription with AI analysis to understand each participant's contributions in your meetings. You'll learn how to capture detailed transcripts that track who said what, then use AI to extract meaningful insights from individual speakers' input.

## Transcription Setup and Recording

<Steps>
  <Step title="Create a Speaker Separation Mode">
    Create a new Custom Mode with these settings:

    * Enable "Identify Speakers" toggle
    * Enable "Record from System Audio" if recording live meetings
    * Select your preferred voice model

    <Tip>While all voice models support speaker separation, Nova (Cloud) delivers the most accurate and reliable results for this feature.</Tip>
  </Step>

  <Step title="Disable AI Processing">
    Disable AI processing initially to speed up transcription. This approach is suggested since Superwhisper currently can't process speaker-separated transcripts with AI in the same mode. Remember to back up your mode's config file before making changes:

    * Navigate to: \~/Documents/superwhisper/modes/
    * Open your mode's JSON file in your preferred text editor
    * Change "languageModelEnabled" from `true` to `false`
    * Save and restart Superwhisper for changes to take effect
  </Step>

  <Step title="Capture & Transcribe Your Meeting">
    Choose your preferred recording method:

    <AccordionGroup>
      <Accordion title="Live Recording">
        * Select your speaker separation mode
        * Start recording
          <Note>Be aware that pressing Escape will stop recording</Note>
      </Accordion>

      <Accordion title="Process Existing Audio">
        * Record meeting with your preferred app
        * Click the Superwhisper menu bar icon
        * Select your speaker separation mode
        * Select "Transcribe File"
        * Choose your audio file
      </Accordion>
    </AccordionGroup>
  </Step>

  <Step title="Access Your Transcript">
    <img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-speaker-separation-001.png" />

    1. Open Superwhisper History
    2. Select the Segments tab
    3. Rename speakers (optional):
       * Click speaker names directly, or
       * Use the right sidebar's Speakers section
    4. Click "Copy to Clipboard" to get the full speaker-separated transcript
  </Step>
</Steps>

***

## AI Processing and Analysis

### Option A: External AI Services

* Use OpenAI, Claude, or your preferred AI provider
* Request your desired analysis on the transcript

### Option B: Superwhisper Custom Mode

<Steps>
  <Step title="Create a new Custom Mode">
    * Write an assistant-focused prompt
    * Enable Application Context
      <Tip>For tips and ideas on how to get the best results with your custom instructions, check these [prompting tips](custom#prompting-tips).</Tip>
  </Step>

  <Step title="Process Your Transcript">
    * Open any text editor
    * Paste your speaker-separated transcript
    * Activate the mode you have just created
    * Dictate your analysis request
  </Step>
</Steps>

### Sample Procesing Requests

```
"Summarize this meeting's key points by speaker"
"Extract action items and assign them to each speaker"
"Show which team members contributed to each key decision"
"Create a participation report showing who discussed which topics in this meeting"
"Break down topic ownership and insights by participant from this meeting's transcript"
```


# Super
Source: https://superwhisper.com/docs/modes/super

Supercharge your dictation with advanced context-aware processing. Super Mode intelligently adapts to your active applications, selected text, and clipboard content to deliver more accurate and relevant results.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-super-001.png" />

## Key Features

**Super Mode enhances your dictation by:**

* Adapting messages to match application context
* Correcting spelling based on app-specific terms, names, and vocabulary
* Converting spoken URLs and emails into proper format
* Preserving message tone and intent while improving clarity

***

## Context Awareness

**Super Mode uses accessibility APIs to gather three types of context:**

<AccordionGroup>
  <Accordion title="1. Application Context">
    * Identifies your active application
    * Reads text from current input fields or text editor
  </Accordion>

  <Accordion title="2. Selected Text Context">
    * Reads any text you've highlighted
    * Uses selection to inform AI processing
  </Accordion>

  <Accordion title="3. Clipboard Context">
    * Incorporates text copied within 3 seconds of dictation, or during dictation
  </Accordion>
</AccordionGroup>

***

## Commands

**Super Mode lets you dictate commands on selected text.** While it understands context, for best result use commands focused on text transformation or formatting rather than content analysis or generation.

<CardGroup>
  <Card title="Correct" icon="circle-check">
    "Make this text title case"
    "Convert selection to uppercase"
    "Format my selected text as bullet points"
  </Card>

  <Card title="Incorrect" icon="circle-xmark">
    "Summarize this paragraph"
    "Expand on these ideas"
    "Rewrite this section"
  </Card>
</CardGroup>

<Tip>**While you can use commands for formatting, they're completely optional.** Just dictate naturally and Super Mode will intelligently adapt to your active app - no text selection or copying needed. It's that simple.</Tip>

***

## Troubleshooting

If you're not getting expected results with Super Mode, check these common issues:

<AccordionGroup>
  <Accordion title="Command Type Mismatch">
    * If you are dictating a command, ensure it is related to formatting or text transformation only
    * Review the Commands section above for examples
  </Accordion>

  <Accordion title="AI Models">
    For optimal results, use one of the following suggested AI models:

    * Claude 3.5 Sonnet
    * GPT-4o Mini
    * GPT-4o
    * Claude 3.5 Haiku
  </Accordion>

  <Accordion title="System Settings & User Error">
    * Check system settings for the correct permissions
    * For application context, make sure the correct app window is active
    * For selected text context, verify that the text is selected when triggering the dictation
    * Text copied to your clipboard will only be processed if done within 3 seconds of starting your dictation or while you're speaking
  </Accordion>

  <Accordion title="Verify Processing">
    Check the History tab to see if context was properly sent to AI. You can view all AI-sent data in the bottom "prompt" field of the right sidebar. This can help you pinpoint if issues come from context capture, voice, or AI processing.
  </Accordion>
</AccordionGroup>

***

<Tip>**Super Mode focuses on context-aware dictation and formatting.** If you need a different type of command with similar smart features, check out [Custom Mode](custom).</Tip>


# Switching Modes
Source: https://superwhisper.com/docs/modes/switching-modes

Learn four convenient ways to switch between Superwhisper modes: keyboard shortcuts, menu bar, auto-activation rules, and deep links. Choose the method that best fits your workflow.

<img style={{ borderRadius: '0.5rem', display: 'block', margin: '0 auto' }} width="80%" src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-switching-006.png" />

## Overview

**Finding your preferred way to switch modes quickly is key to unlocking the full power of Superwhisper.** Whether you're writing emails, taking notes, or crafting messages, smooth mode switching helps you stay in flow while Superwhisper handles the heavy lifting of tailoring your voice input exactly how you need it.

***

## Keyboard Shortcut

A quick way to switch modes just before dictating, while on the recording window.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-switching-001.png" />

1. Trigger dictation to open the recording window
2. Press your configured "Change Mode" keyboard shortcut
3. Hold the modifier key(s) and tap the other key repeatedly to cycle through modes
4. Release when you reach your desired mode

<Note>The active mode is visible only in the large recording window view.</Note>

***

## Menu Bar

Change modes anytime with a quick menu bar click.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-switching-002.png" />

1. Click the Superwhisper menu bar icon
2. Select a new mode from the "Select Mode" submenu

***

## Auto-Activation Rules

Let Superwhisper switch modes automatically based on your active apps and websites. Set up rules in each mode's settings to match your workflow.

[Learn more about auto-activation →](modes#auto-activation-rules)

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-switching-003.png" />

***

## Deep Links

Deep links unlock powerful possibilities for mode switching—perfect for users familiar with automation tools who want to take their workflow to the next level.

**You can use the following deep links with Superwhisper:**

```
superwhisper://mode?key=YOUR_MODE_KEY
superwhisper://record
```

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-switching-005.png" />

**To find a mode's key:**

1. Navigate to \~/Documents/superwhisper/modes
2. Quick Look the mode's JSON file to fine your mode under its `name` key
3. Find the "key" value to use in your deep link

<Tip>Combine both deep links in automation tools to switch modes and start recording in one action. Here's a [sample shortcut](https://www.icloud.com/shortcuts/a925e259d5e84806a700c2a58d4853a4) to get you started.</Tip>

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-switching-004.png" />

***

<Tip>Looking for more advanced switching options? Check out the [Raycast](https://www.raycast.com/nchudleigh/superwhisper) and [Alfred](https://github.com/ognistik/alfred-superwhisper) integrations.</Tip>


# Voice
Source: https://superwhisper.com/docs/modes/voice

Voice Mode provides speed-optimized dictation with basic formatting. Ideal for both quick inputs or longer transcriptions where AI processing is not required.

<img style={{ borderRadius: '0.5rem' }} src="https://mintlify.s3.us-west-1.amazonaws.com/superwhisper/images/modes/modes-voice-001.png" />

## Choosing the Right Model

Since Voice Mode does not include AI processing, it is essential that you carefully choose the voice model according to your expected use case. Some suggestions are listed below, or feel free to explore from all the options available.

**Here's where to start based on your priorities - quick dictation, long recordings, speed, or privacy:**

<Card title="Quick Dictation" icon="bolt" horizontal>
  * **Ultra (Cloud)**: Lightning-fast for short dictations.
  * **Ultra Turbo v3 (Local)**: Great balance of speed and quality, with complete privacy.
</Card>

<Card title="Longer Recordings" icon="stars" horizontal>
  * **Nova (Cloud)**: Ideal for longer recordings where you want to save system resources.
  * **Local Models**: Check the AI Models tab for speed and accuracy specs of each option.
</Card>

***

<Tip>Voice Mode is a transcription-only mode. **For advanced grammar correction or content refinement, consider using other specialized modes.**</Tip>