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_...

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.

---

Prerequisites

1. Deepgram API key

   Sign up at console.deepgram.com. Create a new API key from the dashboard.
2. Mavera API key

   Get your key from Mavera dashboard.
3. Install dependencies

   # Python
   pip install requests websockets
   
   # JavaScript
   npm install ws
   
4. Set environment variables

   export DEEPGRAM_API_KEY="dg_your_deepgram_key"
   export MAVERA_API_KEY="mvra_live_xxxxx"
   

---

Jobs

#	Job	Deepgram Endpoint	Mavera Surface	Output
1	Audio Intelligence → Meeting Analysis	POST /v1/listen (Nova-3 + all intelligence)	Mave Agent (Chat)	Structured meeting intelligence
2	Podcast Analysis Pipeline	POST /v1/listen (topics, paragraphs, utterances)	Mave Agent (Chat)	Content strategy from podcast insights
3	Customer Call Intelligence	POST /v1/listen (diarize, sentiment, utterances)	Mave Agent (Chat)	Messaging playbook from customer language
4	Live Event Transcription → Real-Time Content	WSS /v1/listen (Flux streaming)	Generate	Live blog posts from event stream
5	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

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.

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.

---

All Integrations

Deepgram API Docs

Mave Agent

Generate

Brand Voice

Focus Groups