Deepgram Real-Time Transcription Connector

Streams live audio to Deepgram's WebSocket API at wss://api.deepgram.com/v1/listen for real-time speech-to-text. Handles interim results, utterance detection, and speaker diarization via the Deepgram Node SDK.

Prerequisites

Node.js

Installation

Use the upstream install or setup path that matches your environment:

• npm install @deepgram/sdk
• pnpm install
• make build
• make test

Requirements and caveats from upstream:

• 
• Your proxy must set the Authorization: token DEEPGRAM_API_KEY header and forward requests to Deepgram's API. See our example Deepgram Node Proxy.
• Node.js 18+

Basic usage or getting-started notes:

• bash

• Reference

• API Reference - Complete reference for all SDK methods and parameters

• Source: https://github.com/deepgram/deepgram-js-sdk

• Extracted from upstream docs: https://raw.githubusercontent.com/deepgram/deepgram-js-sdk/HEAD/README.md

Documentation

• https://developers.deepgram.com/docs/node-sdk

Source

• Agent Skill Exchange