> ## 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.

# Cloud Setup Guide

> Recommended cloud provider configuration for maximum speed and accuracy

"og:title": "Stenox Docs"

## Fast, High-Quality Cloud Setup

Cloud providers offer the fastest processing and highest accuracy for Stenox dictation. This guide shows you the recommended configurations for optimal results.

<Tip>
  **Most recommended:** [Stenox Cloud](/providers/transcription/stenox-cloud) — fine-tuned for Stenox, zero configuration, fastest setup. Included with Plus and Lifetime Plus.
</Tip>

## Why Use Cloud Providers?

<CardGroup cols={2}>
  <Card title="Ultra-fast processing" icon="bolt">
    Sub-second transcription and enhancement (5-10x faster than local).
  </Card>

  <Card title="Higher accuracy" icon="bullseye">
    State-of-the-art models optimized for production use.
  </Card>

  <Card title="No local storage" icon="cloud">
    No need to download multi-GB models.
  </Card>

  <Card title="Works on any Mac" icon="computer">
    Intel and Apple Silicon, old and new.
  </Card>
</CardGroup>

## Recommended Cloud Configurations

### Option 1: Stenox Cloud (Most Recommended)

**Best for:** Fastest setup, best out-of-the-box experience

**Configuration:**

* **Transcription:** Stenox Cloud Transcription
* **Enhancement:** Stenox Cloud AI Enhancement

**Setup time:** 2 minutes (just activate your license)
**Processing time:** \~1-2 seconds total
**Availability:** Plus and Lifetime Plus plans

<Steps>
  <Step title="Get Plus or Lifetime Plus">
    Visit [stenox.app/pricing](https://stenox.app/pricing) and choose your plan
  </Step>

  <Step title="Activate License">
    Settings → **License** → Sign in with your purchase email
  </Step>

  <Step title="Select Stenox Cloud">
    Settings → **Transcription** → Provider: **Stenox Cloud**
    Settings → **AI Enhancement** → Provider: **Stenox Cloud**
  </Step>

  <Step title="Start Dictating">
    That's it — no API keys, no configuration, just works
  </Step>
</Steps>

**Why Stenox Cloud?**

* **Fine-tuned for Stenox** — optimized specifically for voice dictation workflows
* **Zero configuration** — no API keys to manage, no accounts to create
* **Consistent quality** — we maintain and update the models for best results
* **Fast and accurate** — production-grade speed and accuracy

<Card title="Learn More" icon="cloud" href="/providers/transcription/stenox-cloud">
  Full Stenox Cloud details
</Card>

***

### Option 2: Maximum Free Credits (BYOK)

**Best for:** Getting started free, maximum free usage

**Configuration:**

* **Transcription:** DeepGram Nova-3 (\$200 free credits)
* **Enhancement:** Google Gemini 2.5 Flash (1,500/day free)

**Setup time:** 10 minutes
**Processing time:** \~1-2 seconds total
**Free usage:** 6-12 months typical

<Steps>
  <Step title="Get DeepGram API key">
    1. Visit [console.deepgram.com](https://console.deepgram.com)
    2. Sign up (no credit card required)
    3. Create API key
    4. **Get \$200 in free credits**
  </Step>

  <Step title="Configure DeepGram in Stenox">
    1. Settings → **Transcription** tab
    2. Provider: **DeepGram**
    3. Paste API key
    4. Model: **Nova-3** (best accuracy)
  </Step>

  <Step title="Get Google Gemini API key">
    1. Visit [aistudio.google.com](https://aistudio.google.com)
    2. Sign in with Google (no credit card)
    3. Create API key
    4. **Get 1,500 free requests/day**
  </Step>

  <Step title="Configure Gemini in Stenox">
    1. Settings → **AI Enhancement** tab
    2. Provider: **Google Gemini**
    3. Paste API key
    4. Model: **Gemini 2.5 Flash** (fastest)
  </Step>
</Steps>

[Get detailed setup instructions →](/guides/free-tier-providers#option-3-maximum-free-credits)

***

### Option 3: Groq Stack (Single API Key)

**Best for:** Simplicity, one account for everything

**Configuration:**

* **Transcription:** Groq Whisper v3-turbo
* **Enhancement:** Groq Llama 3.3 70B or DeepSeek R1

**Setup time:** 5 minutes
**Processing time:** \~1-2 seconds total
**Free usage:** Ongoing free tier with rate limits

<Steps>
  <Step title="Get Groq API key">
    1. Visit [console.groq.com](https://console.groq.com)
    2. Sign up (no credit card required)
    3. Create API key
    4. **One key for both transcription and enhancement!**
  </Step>

  <Step title="Configure Groq Transcription">
    1. Settings → **Transcription** tab
    2. Provider: **Groq**
    3. Paste API key
    4. Model: **whisper-large-v3-turbo**
  </Step>

  <Step title="Configure Groq Enhancement">
    1. Settings → **AI Enhancement** tab
    2. Provider: **Groq**
    3. Paste same API key
    4. Model: **Llama 3.3 70B Versatile**
  </Step>
</Steps>

**Benefits:**

* Single API key management
* Ultra-fast LPU inference
* Ongoing free tier (doesn't expire)
* Simple setup

[Get detailed setup instructions →](/guides/free-tier-providers#option-2-groq-stack-best-free-cloud)

***

### Option 4: Best Quality (Paid BYOK)

**Best for:** Professional use, maximum accuracy

**Configuration:**

* **Transcription:** DeepGram Nova-3 or AssemblyAI Universal-1
* **Enhancement:** Google Gemini 2.5 Pro

**Cost:** \~\$0.75-1.50 per hour of dictation
**Processing time:** \~1-2 seconds total

**When to use:**

* Professional transcription services
* Critical accuracy requirements
* Business or enterprise use
* After free credits are exhausted

***

## Performance Comparison

| Configuration                | Speed | Accuracy | Setup   | Cost               | Best For                     |
| ---------------------------- | ----- | -------- | ------- | ------------------ | ---------------------------- |
| **Stenox Cloud**             | ⚡⚡⚡   | ⭐⭐⭐⭐⭐    | Instant | Plus/Lifetime Plus | Best experience, zero config |
| **DeepGram + Gemini**        | ⚡⚡⚡   | ⭐⭐⭐⭐     | 10 min  | \$\$ after free    | Maximum free credits         |
| **Groq Stack**               | ⚡⚡⚡   | ⭐⭐⭐⭐     | 5 min   | Free tier          | One API key simplicity       |
| **AssemblyAI + Gemini**      | ⚡⚡⚡   | ⭐⭐⭐⭐     | 10 min  | \$                 | Accent optimization          |
| **Local (WhisperKit + MLX)** | ⚡     | ⭐⭐⭐      | 5 min   | Free forever       | Privacy, offline             |

## Detailed Provider Configurations

### DeepGram Nova-3 Settings

**Recommended configuration:**

| Setting         | Value                    | Why                        |
| --------------- | ------------------------ | -------------------------- |
| **Model**       | Nova-3                   | Latest, best accuracy      |
| **Language**    | English (or auto-detect) | Optimize for your language |
| **Streaming**   | Enabled (automatic)      | Fastest results            |
| **Punctuation** | Enabled (automatic)      | Auto-punctuation           |

**In Stenox:**

* Provider: DeepGram
* Model: Nova-3 or Nova-3-English
* Language: English or Auto-detect

[DeepGram full guide →](/providers/transcription/deepgram)

### Google Gemini 2.5 Flash Settings

**Recommended configuration:**

| Setting           | Value                   | Why                            |
| ----------------- | ----------------------- | ------------------------------ |
| **Model**         | Gemini 2.5 Flash        | Fastest with excellent quality |
| **Custom prompt** | Default or Professional | Based on use case              |
| **Temperature**   | Default                 | Stenox handles this            |

**In Stenox:**

* Provider: Google Gemini
* Model: Gemini 2.5 Flash
* Custom prompt: (optional, see below)

[Google Gemini full guide →](/providers/llm/google-gemini)

### Enhancement Prompts

<Tip>
  **Fine-tuned out of the box.** Both Stenox Cloud and local providers come with fine-tuned enhancements that we continue to refine — no configuration needed for most users.
</Tip>

For BYOK providers, you can configure custom enhancement behaviors:

<Tabs>
  <Tab title="Default (General Use)">
    ```
    Fix grammar and punctuation errors.
    Keep the original meaning and tone unchanged.
    ```

    **Use for:** General dictation, notes
  </Tab>

  <Tab title="Professional Email">
    ```
    Fix grammar and rewrite in a professional, business-appropriate tone.
    Format as a clear, concise email.
    Remove filler words and make it direct.
    Use proper email structure.
    ```

    **Use for:** Work emails, business communications
  </Tab>

  <Tab title="Technical Documentation">
    ```
    Fix grammar and format for technical documentation.
    Preserve all technical terms and code exactly as stated.
    Use active voice and clear, concise language.
    Format code blocks appropriately.
    ```

    **Use for:** Code comments, documentation, technical writing
  </Tab>
</Tabs>

## Multi-Profile Cloud Setup

For maximum flexibility, create profiles for different scenarios:

### Profile Strategy

<Steps>
  <Step title="Work Email Profile">
    * **Name:** "Work Email"
    * **Transcription:** DeepGram Nova-3
    * **Enhancement:** Gemini 2.5 Flash
    * **Custom prompt:** Professional email tone
    * **Auto-activate:** When Gmail or Outlook is active
  </Step>

  <Step title="Quick Notes Profile">
    * **Name:** "Quick Notes"
    * **Transcription:** Groq Whisper (fastest)
    * **Enhancement:** None (skip for speed)
    * **Auto-activate:** When Notes app is active
  </Step>

  <Step title="Documentation Profile">
    * **Name:** "Documentation"
    * **Transcription:** DeepGram Nova-3
    * **Enhancement:** Gemini 2.5 Flash
    * **Custom prompt:** Technical documentation
    * **Auto-activate:** When VSCode or similar is active
  </Step>

  <Step title="Fallback Local Profile">
    * **Name:** "Offline"
    * **Transcription:** WhisperKit
    * **Enhancement:** MLX or None
    * **Manual activation:** When internet unavailable
  </Step>
</Steps>

[Learn about Profiles →](/profiles/creating-profiles)

## Usage Optimization

### Maximize Free Credits

**DeepGram (\$200 credits):**

* Use for important dictation (work emails, documents)
* Switch to Groq or local for casual notes
* Track usage in DeepGram console

**Google Gemini (1,500/day):**

* More than enough for most users
* If you hit limit, create "no enhancement" profile
* Resets daily at midnight PST

**Groq (free tier):**

* Use as primary option — no API costs
* Rate limits refresh quickly
* Good for privacy-conscious users who prefer not to create accounts

### Cost Control

After free tiers, control costs:

<AccordionGroup>
  <Accordion title="Use Groq free tier as primary" icon="bolt">
    Groq's ongoing free tier is sufficient for most personal use. Only upgrade if you consistently hit rate limits.
  </Accordion>

  <Accordion title="Skip enhancement for quick notes" icon="clock">
    Create a profile without AI enhancement for quick personal notes. Saves on Gemini API calls.
  </Accordion>

  <Accordion title="Switch to local for high-volume" icon="computer">
    If you dictate heavily (2+ hours/day), switch to WhisperKit + MLX to avoid costs.
  </Accordion>

  <Accordion title="Use AssemblyAI after DeepGram" icon="arrows-rotate">
    AssemblyAI costs only \$0.0009/min after free credits - very affordable for continued use.
  </Accordion>
</AccordionGroup>

## Troubleshooting Cloud Setup

<AccordionGroup>
  <Accordion title="Slow processing despite cloud providers" icon="hourglass">
    * Check your internet connection speed
    * Try switching to different model (e.g., Flux instead of Nova-3)
    * Check provider status pages for outages
    * Test with local provider to isolate issue
  </Accordion>

  <Accordion title="Poor transcription accuracy" icon="spell-check">
    * Ensure you're using Nova-3 or latest models
    * Check microphone input device (Settings → Audio tab)
    * Reduce background noise
    * Speak more clearly or use better microphone
    * Try AssemblyAI if you have strong accent
  </Accordion>

  <Accordion title="API errors or authentication failures" icon="triangle-exclamation">
    * Verify API keys are correct (no extra spaces)
    * Check API key status in provider dashboards
    * Ensure you have remaining credits/quota
    * Try creating new API keys
  </Accordion>

  <Accordion title="Hit rate limits frequently" icon="gauge-high">
    * Create local fallback profile (WhisperKit + MLX)
    * Set up multiple cloud providers and rotate
    * Consider upgrading to paid tier if needed
  </Accordion>
</AccordionGroup>

## Internet Connection Requirements

**Minimum requirements:**

* **Speed:** 1 Mbps upload, 1 Mbps download
* **Latency:** \< 100ms preferred
* **Stability:** Consistent connection (not intermittent)

**Optimal:**

* **Speed:** 5+ Mbps upload/download
* **Latency:** \< 50ms
* **Type:** Wi-Fi or Ethernet (not cellular for best results)

<Note>
  Cloud processing sends \~1 MB per minute of audio. Most home internet connections are more than sufficient.
</Note>

## Next Steps

<CardGroup cols={2}>
  <Card title="Free Tier Guide" icon="gift" href="/guides/free-tier-providers">
    Maximize free usage across all cloud providers.
  </Card>

  <Card title="Create Profiles" icon="layer-group" href="/profiles/creating-profiles">
    Set up different profiles for different scenarios.
  </Card>

  <Card title="DeepGram Setup" icon="microphone" href="/providers/transcription/deepgram">
    Complete DeepGram configuration guide.
  </Card>

  <Card title="Gemini Setup" icon="sparkles" href="/providers/llm/google-gemini">
    Complete Google Gemini configuration guide.
  </Card>
</CardGroup>

<Tip>
  **Best setup:** Stenox Cloud — fine-tuned for Stenox, zero configuration, just works. Get started at [stenox.app/pricing](https://stenox.app/pricing).
</Tip>