> ## 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.

# Voice to Text

> Voice to Text 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://mintcdn.com/superwhisper-docs-cloud-model-rate-limits/mT9O_ARPZT3-tjer/images/modes/modes-voice-001.png?fit=max&auto=format&n=mT9O_ARPZT3-tjer&q=85&s=77b24ec38b5e59314133c118ab489a3c" alt="Superwhisper's interface for Voice Mode" width="1718" height="770" data-path="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>
  * **Parakeet (Local)**: Lightning-fast for short dictations (in English only).
  * **Ultra (Cloud)**: Fast, versatile, and accurate.
  * **Ultra Turbo v3 (Local)**: Great balance of speed and quality, with complete privacy.
</Card>

<Card title="Longer Recordings" icon="stars" horizontal>
  * **Nova (Cloud)**: Recommended for longer recordings and best for handling speaker separation.
  * **Other Models**: All models can process extended recordings with varying speeds and accuracy.
</Card>

<img style={{ borderRadius: '0.5rem' }} src="https://mintcdn.com/superwhisper-docs-cloud-model-rate-limits/mT9O_ARPZT3-tjer/images/modes/modes-voice-002.png?fit=max&auto=format&n=mT9O_ARPZT3-tjer&q=85&s=e614d79b1a20451904d423d1c9bbca5e" alt="Superwhisper's List of Models" width="1124" height="633" data-path="images/modes/modes-voice-002.png" />

In the advanced settings, you can review detailed specifications for each local model—such as speed, language support, and accuracy—to help you select the most appropriate option for your needs.

***

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