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.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Deepgram Real-Time Transcription Connector"
slug: "deepgram-realtime-transcription-connector"
description: "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."
github_stars: 260
verification: "security_reviewed"
source: "https://github.com/deepgram/deepgram-js-sdk"
author: "Deepgram"
category: "Media & Transcription"
framework: "MCP"
tool_ecosystem:
github_repo: "deepgram/deepgram-js-sdk"
github_stars: 260
npm_package: "@deepgram/sdk"
npm_weekly_downloads: 1571012
---
# 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:
- [](https://nodejs.org/)
- Your proxy must set the Authorization: token DEEPGRAM_API_KEY header and forward requests to Deepgram's API. See our example [Deepgram Node Proxy](https://github.com/deepgram-devs/deepgram-node-proxy).
- Node.js 18+
Basic usage or getting-started notes:
- bash
- ## Reference
- **[API Reference](./reference.md)** - 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](https://agentskillexchange.com/skills/deepgram-realtime-transcription-connector/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.