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

# Deepgram

> 5 production-ready jobs — audio intelligence meeting analysis, podcast content strategy, customer call messaging playbooks, live event streaming to real-time blog posts, and voice-of-customer brand voice extraction

Deepgram's speech AI platform — Nova-3 for pre-recorded transcription with audio intelligence (sentiment, topics, entities, intents, summaries), Flux for real-time streaming, and Aura-2 for text-to-speech — pairs with Mavera to turn spoken content into structured marketing intelligence. These five jobs chain Deepgram endpoints with Mavera surfaces to analyze meetings with full audio intelligence, mine podcasts for content strategy, extract messaging playbooks from customer calls, produce live blog posts from streaming event transcription, and build customer-authentic brand voices from interview recordings.

***

## API Reference Card

| Detail                 | Value                                                                                               |
| ---------------------- | --------------------------------------------------------------------------------------------------- |
| **Base URL**           | `https://api.deepgram.com`                                                                          |
| **Auth**               | Token — `Authorization: Token dg_xxxxx`                                                             |
| **Key models**         | Nova-3 (pre-recorded), Flux (streaming), Aura-2 (TTS)                                               |
| **Key endpoints**      | `POST /v1/listen` (transcription), `WSS /v1/listen` (streaming), `POST /v1/speak` (TTS)             |
| **Audio intelligence** | Summarization, topic detection, entity detection, sentiment analysis, intent detection, diarization |
| **Mavera base**        | `https://app.mavera.io/api/v1`                                                                      |
| **Mavera auth**        | `Authorization: Bearer mvra_live_...`                                                               |

<Info>
  All examples use two environment variables: `DEEPGRAM_API_KEY` (your Deepgram key starting with `dg_`) and `MAVERA_API_KEY` (your Mavera key starting with `mvra_live_`). Deepgram uses `Authorization: Token` — **not** `Bearer`. Never commit either key to version control.
</Info>

***

## Prerequisites

<Steps>
  <Step title="Deepgram API key">Sign up at [console.deepgram.com](https://console.deepgram.com). Create a new API key from the dashboard.</Step>
  <Step title="Mavera API key">Get your key from [Mavera dashboard](https://app.mavera.io/settings/api-keys).</Step>

  <Step title="Install dependencies">
    ```bash theme={"dark"}
    # Python
    pip install requests websockets

    # JavaScript
    npm install ws
    ```
  </Step>

  <Step title="Set environment variables">
    ```bash theme={"dark"}
    export DEEPGRAM_API_KEY="dg_your_deepgram_key"
    export MAVERA_API_KEY="mvra_live_xxxxx"
    ```
  </Step>
</Steps>

***

## Jobs

| # | Job                                                                                         | Deepgram Endpoint                                | Mavera Surface    | Output                                    |
| - | ------------------------------------------------------------------------------------------- | ------------------------------------------------ | ----------------- | ----------------------------------------- |
| 1 | [Audio Intelligence → Meeting Analysis](/integrations/deepgram/audio-intelligence-meetings) | POST /v1/listen (Nova-3 + all intelligence)      | Mave Agent (Chat) | Structured meeting intelligence           |
| 2 | [Podcast Analysis Pipeline](/integrations/deepgram/podcast-analysis)                        | POST /v1/listen (topics, paragraphs, utterances) | Mave Agent (Chat) | Content strategy from podcast insights    |
| 3 | [Customer Call Intelligence](/integrations/deepgram/customer-call-intelligence)             | POST /v1/listen (diarize, sentiment, utterances) | Mave Agent (Chat) | Messaging playbook from customer language |
| 4 | [Live Event Transcription → Real-Time Content](/integrations/deepgram/live-event-content)   | WSS /v1/listen (Flux streaming)                  | Generate          | Live blog posts from event stream         |
| 5 | [Voice of Customer → Brand Voice](/integrations/deepgram/voice-of-customer-brand-voice)     | POST /v1/listen (batch interviews)               | Brand Voices      | Customer-authentic brand voice profile    |

***

## Rate Limits & Production Notes

| Deepgram Feature                     | Limit                              | Strategy                                    |
| ------------------------------------ | ---------------------------------- | ------------------------------------------- |
| Pre-recorded `/v1/listen` (Nova-3)   | Concurrency-based (plan-dependent) | Queue files; 2s delay between calls         |
| Streaming `/v1/listen` (Flux/Nova-3) | 1 connection per concurrent stream | Reconnect with exponential backoff          |
| Audio intelligence features          | Same as base transcription         | No extra limits — features are query params |
| File size                            | Up to 2 GB per request             | Split larger files with ffmpeg              |

<Tip>
  Deepgram charges by audio duration, not API calls. A 60-minute file costs the same as one request or six 10-minute chunks. Prefer single large requests. Monitor usage at [console.deepgram.com](https://console.deepgram.com).
</Tip>

<Warning>
  Deepgram uses `Authorization: Token` — **not** `Bearer`. Every request needs `Token {key}`. The most common integration error is using `Bearer`, which returns 401. For streaming, pass the token as a WebSocket header — not a query parameter. Monitor Mavera credits at [Dashboard](https://app.mavera.io/settings/usage).
</Warning>

***

<CardGroup cols={3}>
  <Card title="All Integrations" icon="plug" href="/integrations" />

  <Card title="Deepgram API Docs" icon="microphone" href="https://developers.deepgram.com/docs" />

  <Card title="Mave Agent" icon="brain" href="/features/mave-agent" />

  <Card title="Generate" icon="pen" href="/features/generate" />

  <Card title="Brand Voice" icon="comment" href="/features/brand-voices" />

  <Card title="Focus Groups" icon="users" href="/features/focus-groups" />
</CardGroup>