> ## Documentation Index
> Fetch the complete documentation index at: https://superwhisper-docs-cloud-model-rate-limits.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Language Detection

> Learn how to fix issues with Superwhisper automatically translating non-English dictation to English when using the Automatic language setting.

## Overview

Superwhisper processes your dictation in two distinct stages:

1. **Voice-to-Text Transcription**: Converting your spoken words into written text
2. **AI Text Processing**: Applying formatting and handling specific requests based on the selected mode

When using the "Automatic" language setting, you may experience your non-English dictation being incorrectly transcribed as English text. This mostly happens at the transcription stage, before any AI processing occurs.

<Info>
  You can verify this by checking [the History tab](../get-started/interface-history), which shows the raw transcription before processing.
</Info>

***

## Why This Happens

The transcription AI models use a prompt to guide their behavior. This prompt:

* Improves word recognition accuracy
* Enhances punctuation
* Can unintentionally affect language detection

With the "Automatic" setting, Superwhisper cannot predict which languages you'll use, making it challenging to provide appropriate language guidance to the transcription model.

***

## Solution: The Vocabulary Hint

You can significantly improve automatic language detection by adding a simple phrase to your Vocabulary list:

<Steps>
  <Step title="Open Vocabulary Settings">
    Navigate to the Vocabulary tab in SuperWhisper settings.
  </Step>

  <Step title="Add Phrase in Your Language">
    Add the phrase "and it can also include words in \[LANGUAGE]" written in your target language. For example, if you speak Spanish, add: "y también puede incluir palabras en español".

    <img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper-docs-cloud-model-rate-limits/pbQcuJvzOhF7n2dL/images/common-issues/language-detection-001.png?fit=max&auto=format&n=pbQcuJvzOhF7n2dL&q=85&s=6544d838654f3310d5b95c88cc61b5be" alt="Superwhisper Vocabulary Hint for Language Detection" width="1674" height="976" data-path="images/common-issues/language-detection-001.png" />
  </Step>

  <Step title="Additional Considerations">
    For best results, add a few more individual words to your vocabulary and keep the list short for optimal performance.
  </Step>
</Steps>

***

## Model Compatibility

**The vocabulary hint works effectively with all voice models except Nova or Parakeet.** Nova and Parakeet models don't support multiple languages within the same dictation session. You can still add the vocabulary phrase without negative effects, but you won't get the multi-language benefits.

<Tip>
  With models that support the vocabulary hint, you'll get much better language recognition. You can also switch between multiple languages in a single session without having to adjust any settings.
</Tip>

***

## Alternative Approach

If the vocabulary hack doesn't fully address your needs:

1. **Create Language-Specific Modes**: Set up different modes for each language you use regularly
2. **Custom Mode Prompts**: For custom modes, add instructions to preserve the input language

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Using Vocabulary" icon="book-open" href="../get-started/interface-vocabulary">
    Learn how to use the Vocabulary feature to guide and enhance your transcription accuracy.
  </Card>

  <Card title="Speaker Separated Meetings" icon="users" href="../modes/speaker-separated-meetings">
    Discover how to use Nova models to transcribe audio with automatic speaker identification.
  </Card>
</CardGroup>