> ## 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.

# DeepGram

> Ultra-fast cloud transcription with Nova-3 models

"og:title": "Stenox Docs"

<Warning>
  This is a **TRANSCRIPTION** provider. It converts your speech to text.
  For AI enhancement like grammar correction, see [AI Enhancement Providers](/providers/overview#ai-enhancement-providers).
</Warning>

## Overview

DeepGram is a leading speech-to-text API known for speed and accuracy. Their Nova-3 model delivers state-of-the-art transcription with sub-second processing times.

**Key Benefits:**

* ⚡ **Ultra-fast** - Sub-second transcription processing
* 🎯 **High accuracy** - Nova-3 achieves industry-leading word error rates
* 🌐 **30+ languages** - Auto-language detection included
* 🎁 **\$200 free credits** - Generous free tier for new users

## Free Tier

<Tip>
  **New DeepGram users get \$200 in free credits!**

  That's approximately **15,000+ minutes** of transcription - enough for months of regular use.

  **No credit card required** to sign up and claim your credits.
</Tip>

### What You Get

* **\$200 in credits** upon signup
* **No credit card required** for free tier
* **No expiration** on credits (for active accounts)
* **All features included** - Nova-3, streaming, punctuation, etc.

After credits are used, pay-as-you-go pricing starts at \$0.0125 per minute.

## Getting Your Free API Key

<Steps>
  <Step title="Visit DeepGram Console">
    Go to [console.deepgram.com](https://console.deepgram.com) in your browser.
  </Step>

  <Step title="Sign up for free">
    Click **Sign Up** and create an account with:

    * Email address
    * Password
    * Or sign in with Google/GitHub

    **No credit card required!**
  </Step>

  <Step title="Verify your email">
    Check your email inbox for a verification link from DeepGram and click it to confirm your account.
  </Step>

  <Step title="Navigate to API Keys">
    Once logged in:

    1. Click on your project name (usually "Default Project")
    2. Go to the **API Keys** section in the left sidebar
  </Step>

  <Step title="Create a new API key">
    1. Click **Create New Key**
    2. Give it a name (e.g., "Stenox")
    3. Copy the API key - you won't be able to see it again!
  </Step>

  <Step title="Add key to Stenox">
    1. Open Stenox Settings
    2. Go to **Transcription** tab
    3. Select **DeepGram** as provider
    4. Paste your API key
    5. Choose your model (Nova-3 recommended)
    6. Click **Save**
  </Step>
</Steps>

<Note>
  **Keep your API key secure!** Treat it like a password. Don't share it publicly or commit it to version control.
</Note>

## Available Models

DeepGram offers several model variants:

### Nova-3 (Recommended)

**Latest and best model:**

* State-of-the-art accuracy
* Fastest processing (\< 1 second)
* Best for: All use cases, default choice

**Variants:**

* `nova-3` - Standard, multilingual
* `nova-3-english` - Optimized for English

### Nova-2

**Previous generation:**

* Still excellent accuracy
* Slightly cheaper than Nova-3
* Best for: Budget-conscious users

**Variants:**

* `nova-2` - Standard, multilingual
* `nova-2-english` - Optimized for English

### Flux

**Fast, cost-effective option:**

* Good accuracy for general use
* Cheaper than Nova models
* Best for: High-volume, non-critical transcription

<Tip>
  **Recommendation:** Start with **Nova-3** for the best experience. Your \$200 in credits will last a very long time.
</Tip>

## Language Support

DeepGram supports 30+ languages with auto-detection:

**Supported Languages:**

* English (US, UK, Australian, Indian accents)
* Spanish (Spain, Latin America)
* French, German, Italian, Portuguese
* Dutch, Polish, Russian, Turkish
* Chinese (Mandarin), Japanese, Korean, Hindi
* And many more...

**Auto-Detection:**

* Enable in Stenox profile settings
* DeepGram automatically identifies the language being spoken
* Works across all supported languages

## Configuration in Stenox

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

  <Step title="Go to Transcription tab">
    Select the **Transcription** tab
  </Step>

  <Step title="Select DeepGram">
    Choose **DeepGram** from the provider dropdown
  </Step>

  <Step title="Enter API key">
    Paste your API key (from console.deepgram.com)
  </Step>

  <Step title="Choose model">
    Select **Nova-3** (recommended) or another model
  </Step>

  <Step title="Configure language">
    * For English-only: Select `English`
    * For multilingual: Select `Auto-detect` or specific language
  </Step>

  <Step title="Save settings">
    Click **Save** to activate DeepGram
  </Step>
</Steps>

## Features

### Streaming Transcription

DeepGram uses WebSocket streaming for real-time results:

* Audio is sent as you speak
* Transcription begins immediately
* Results return in \< 1 second after you stop speaking

### Automatic Punctuation

DeepGram automatically adds punctuation:

* Periods, commas, question marks
* Capitalization of proper nouns
* Natural sentence structure

No need to say "comma" or "period" - it's added automatically based on context.

### Speaker Adaptation

DeepGram adapts to your voice:

* Learns your speaking patterns
* Improves accuracy over time
* Better recognition of frequently used terms

## Performance

**Expected processing times with DeepGram:**

| Recording Length | Processing Time |
| ---------------- | --------------- |
| 5 seconds        | \< 0.5 seconds  |
| 10 seconds       | \< 1 second     |
| 30 seconds       | 1-2 seconds     |
| 60 seconds       | 2-3 seconds     |

<Tip>
  DeepGram is typically **5-10x faster** than local WhisperKit processing.
</Tip>

## Usage Tracking

Monitor your credit usage in the DeepGram console:

1. Visit [console.deepgram.com](https://console.deepgram.com)
2. Go to **Billing** in the sidebar
3. View:
   * Remaining credits (\$200 initially)
   * Usage this month
   * Detailed usage logs

<Note>
  Stenox does not track your DeepGram usage. Check the DeepGram console for accurate credit balance.
</Note>

## Privacy Considerations

**What DeepGram sees:**

* Your audio is sent to DeepGram servers for processing
* DeepGram may log audio and transcripts for quality improvement
* Data is encrypted in transit (HTTPS/WSS)

**If privacy is critical:**

* Use [WhisperKit (local)](/providers/transcription/whisperkit-local) for 100% private transcription
* Or review DeepGram's privacy policy and data retention settings

## When to Use DeepGram

<CardGroup cols={2}>
  <Card title="Maximum accuracy" icon="bullseye">
    Nova-3 delivers state-of-the-art transcription quality.
  </Card>

  <Card title="Speed matters" icon="bolt">
    Sub-second processing for near-instant results.
  </Card>

  <Card title="Professional use" icon="briefcase">
    Reliable for business emails, documents, and presentations.
  </Card>

  <Card title="Free cloud option" icon="gift">
    \$200 in credits provides generous free usage.
  </Card>
</CardGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="API key invalid or not working" icon="key">
    * Ensure you copied the entire key (no spaces or extra characters)
    * Check that the key is active in DeepGram console
    * Try creating a new API key
    * Verify your DeepGram account is verified (check email)
  </Accordion>

  <Accordion title="Transcription fails or times out" icon="clock">
    * Check your internet connection
    * Verify you have remaining credits in DeepGram console
    * Try a different model (Nova-2 or Flux)
    * Check Stenox logs for error messages
  </Accordion>

  <Accordion title="Poor accuracy or wrong words" icon="spell-check">
    * Ensure you're using Nova-3 (best accuracy)
    * Check language setting matches your speech
    * Reduce background noise
    * Speak more clearly or use a better microphone
    * Add custom vocabulary in Stenox settings
  </Accordion>

  <Accordion title="Running out of credits quickly" icon="credit-card">
    * Check usage in DeepGram console (Billing → Usage)
    * Switch to Flux model for cheaper transcription
    * Use WhisperKit (local) when privacy isn't critical to preserve credits
    * Create profiles to automatically switch based on use case
  </Accordion>
</AccordionGroup>

## Pricing After Free Credits

Once your \$200 in credits are used:

| Model  | Price per Minute | Price per Hour |
| ------ | ---------------- | -------------- |
| Nova-3 | \$0.0125         | \$0.75         |
| Nova-2 | \$0.0100         | \$0.60         |
| Flux   | \$0.0050         | \$0.30         |

**Example usage:**

* 1 hour of dictation per day = \~\$22.50/month (Nova-3)
* 30 minutes per day = \~\$11.25/month (Nova-3)

[View full pricing →](https://deepgram.com/pricing)

## Next Steps

<CardGroup cols={2}>
  <Card title="Add AI Enhancement" icon="sparkles" href="/providers/llm/google-gemini">
    Combine with Google Gemini for grammar correction and formatting.
  </Card>

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

  <Card title="Free Tier Guide" icon="gift" href="/guides/free-tier-providers">
    Maximize your free credits across all providers.
  </Card>

  <Card title="Cloud Setup Guide" icon="cloud" href="/guides/cloud-setup">
    Recommended cloud configuration for best results.
  </Card>
</CardGroup>