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

# 100% Local Privacy

> Complete privacy with local-only processing

"og:title": "Stenox Docs"

## Complete Privacy

Stenox can operate **100% locally** on your Mac. When using local providers, your audio and text never leave your device — perfect for sensitive content, confidential work, or anywhere privacy matters.

<Tip>
  **100% Private = Parakeet or WhisperKit (transcription) + MLX (AI enhancement)**

  No internet required. No API keys. No cloud services. Complete privacy.
</Tip>

## Local Providers

<CardGroup cols={3}>
  <Card title="Parakeet" icon="microphone" href="/providers/transcription/parakeet-local">
    **Local Transcription**

    NVIDIA's state-of-the-art speech model. Best accuracy with CoreML optimization on Apple Neural Engine.
  </Card>

  <Card title="WhisperKit" icon="microphone" href="/providers/transcription/whisperkit-local">
    **Local Transcription**

    Apple's optimized Whisper implementation. Lightweight models for fast, private speech-to-text.
  </Card>

  <Card title="MLX" icon="sparkles" href="/providers/llm/mlx-local">
    **Local AI Enhancement**

    Apple's ML framework running efficient language models. Grammar correction and formatting without cloud.
  </Card>
</CardGroup>

## Why Go Local?

<CardGroup cols={2}>
  <Card title="Complete Confidentiality" icon="lock">
    Healthcare, legal, financial, or any sensitive content stays on your Mac.
  </Card>

  <Card title="Offline Functionality" icon="wifi-slash">
    Works on airplanes, in remote locations, or when internet is unavailable.
  </Card>

  <Card title="No Third Parties" icon="shield-check">
    Your data is never sent to external services or servers.
  </Card>

  <Card title="No API Costs" icon="dollar-sign">
    No per-minute charges or API fees. Processing happens on your Mac.
  </Card>
</CardGroup>

## Quick Setup

<Steps>
  <Step title="Open Stenox Settings">
    Click the Stenox menu bar icon → **Settings**
  </Step>

  <Step title="Configure Transcription">
    Go to **Models** tab → Set **Transcription Provider** to **Parakeet** (recommended) or **WhisperKit** → Download a model
  </Step>

  <Step title="Configure AI Enhancement">
    In the same tab → Set **AI Enhancement Provider** to **MLX** → Download a model (Gemma 3n 2B recommended)
  </Step>

  <Step title="Verify Offline">
    Turn off Wi-Fi → Test a dictation → It works!
  </Step>
</Steps>

## Requirements

<Note>
  **MLX requires Apple Silicon.** Intel Mac users can still use WhisperKit for local transcription, but must use cloud providers for AI enhancement.
</Note>

## Model Options

### Parakeet (Transcription) — Recommended

| Model           | Size     | Speed     | Best For                     |
| --------------- | -------- | --------- | ---------------------------- |
| **Parakeet v2** | \~2.5 GB | Very Fast | English only, best accuracy  |
| **Parakeet v3** | \~2.5 GB | Very Fast | Multilingual (25+ languages) |

### WhisperKit (Transcription)

| Model        | Size   | Speed  | Best For                      |
| ------------ | ------ | ------ | ----------------------------- |
| **base.en**  | 142 MB | Fast   | English only, quick setup     |
| **small.en** | 483 MB | Medium | English, better accuracy      |
| **base**     | 142 MB | Fast   | Multilingual (100+ languages) |
| **small**    | 483 MB | Medium | Multilingual, better accuracy |

### MLX (AI Enhancement)

| Model             | Size     | Speed   | Best For                   |
| ----------------- | -------- | ------- | -------------------------- |
| **Qwen 2.5 1.5B** | \~1 GB   | Fastest | Quick tasks, 8GB Macs      |
| **Gemma 3n 2B**   | \~1.2 GB | Fast    | Best accuracy, recommended |
| **Phi-3 Mini**    | \~2.4 GB | Medium  | Balanced quality           |
| **Gemma 3n 4B**   | \~2.5 GB | Slower  | Higher quality             |

## Performance

Processing times with local providers:

| Configuration                   | Total Time      |
| ------------------------------- | --------------- |
| Parakeet v2 only                | \~2-3 seconds   |
| Parakeet v2 + MLX Qwen 1.5B     | \~4-6 seconds   |
| WhisperKit base.en only         | \~3-5 seconds   |
| WhisperKit + MLX Qwen 1.5B      | \~5-7 seconds   |
| WhisperKit small.en + MLX Phi-3 | \~10-12 seconds |

<Note>
  Local processing is slower than cloud (which can be \~1-2 seconds), but provides complete privacy.
</Note>

## Privacy Use Cases

<AccordionGroup>
  <Accordion title="Healthcare & Medical" icon="heart-pulse">
    HIPAA compliance, patient confidentiality. Use with EMR/EHR applications and custom medical vocabulary.
  </Accordion>

  <Accordion title="Legal Work" icon="scale-balanced">
    Attorney-client privilege, confidential documents. Add legal terminology to vocabulary.
  </Accordion>

  <Accordion title="Financial Services" icon="building-columns">
    Client confidentiality, regulatory compliance. Works offline for secure environments.
  </Accordion>

  <Accordion title="Journalism" icon="newspaper">
    Source protection, sensitive investigations. No data leaves your device.
  </Accordion>

  <Accordion title="Personal Privacy" icon="user-lock">
    Personal preference, data sovereignty. Complete control over your data.
  </Accordion>
</AccordionGroup>

## Hybrid Approach

Want privacy for audio but cloud quality for text enhancement?

* **Transcription:** Parakeet or WhisperKit (local) — Audio stays private
* **Enhancement:** Google Gemini or Groq (cloud) — Text enhanced with top-tier models

This keeps your most sensitive data (audio recordings) local while leveraging cloud AI for better text quality.

## Next Steps

<CardGroup cols={2}>
  <Card title="Parakeet Guide" icon="microphone" href="/providers/transcription/parakeet-local">
    Best accuracy local transcription setup.
  </Card>

  <Card title="WhisperKit Guide" icon="microphone" href="/providers/transcription/whisperkit-local">
    Lightweight local transcription setup.
  </Card>

  <Card title="MLX Guide" icon="sparkles" href="/providers/llm/mlx-local">
    Complete local AI enhancement setup.
  </Card>

  <Card title="Create Profiles" icon="sliders" href="/profiles/creating-profiles">
    Different providers for different contexts.
  </Card>
</CardGroup>