OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add deepgram/skills --skill examples
Find working Deepgram integration examples with third-party platforms and frameworks. Use whenever someone wants to integrate Deepgram with Twilio, LiveKit, LangChain, Vercel AI SDK, Discord, Vonage, Pipecat, Expo, FastAPI, Cloudflare Workers, Slack, Telegram, LlamaIndex, Zoom, Next.js, Nuxt, Django, SvelteKit, NestJS, Spring Boot, CrewAI, Riverside, SignalWire, and more. Examples are full runnable integration demos, not minimal feature snippets.
npx skills add deepgram/skills --skill examples
Working examples showing how to use Deepgram with popular platforms, frameworks, and ecosystems.
Use a different skill when:
recipes skillstarters skillapi skillRepository: https://github.com/deepgram/examples
Examples are numbered (010, 020, ...) and each is a self-contained integration.
| Category | Integrations | Common STT choice |
|---|---|---|
| Telephony | Twilio, Vonage, SignalWire, Daily.co, Asterisk/FreeSWITCH | Nova live (/v1/listen) for call transcription; Flux STT (/v2/listen) for AI-agent calls |
| Voice AI frameworks | LiveKit Agents, Pipecat, OpenAI Agents SDK, CrewAI | Flux STT (/v2/listen) — built-in turn detection; or Voice Agent (/v1/agent/converse) for full-pipeline |
| Chat platforms | Discord, Slack, Telegram | Nova prerecorded (/v1/listen) for attachments |
| Web frameworks | Next.js, Nuxt, Django, SvelteKit, NestJS, Express + React, FastAPI, Spring Boot | Nova live (/v1/listen) for captions; Nova prerecorded for batch |
| Mobile / desktop | Expo, Flutter, Swift iOS, Kotlin Android, Tauri, Electron | Nova live (/v1/listen); Flux STT (/v2/listen) if the app is a voice agent |
| Cloud / serverless | AWS Lambda, Cloudflare Workers | Nova prerecorded (/v1/listen) — best fit for request/response |
| Recording platforms | Zoom, Riverside.fm | Nova prerecorded (/v1/listen) |
| Browser / no-bundler | Vanilla JavaScript | Nova live (/v1/listen) via the Browser SDK |
| LLM frameworks | LangChain, LlamaIndex, Vercel AI SDK | Nova or Flux STT depending on streaming vs batch |
| Low-code / automation | n8n community nodes | Nova (/v1/listen) for event-driven transcription |
The column above is the STT half of each integration. On the TTS side, Aura (/v1/speak) is what these examples use today — no example in the repo covers Flux TTS (/v2/speak) yet, even in the telephony and voice-AI-framework categories where it fits best. If you're wiring Flux TTS into one of these platforms, take the integration's transport and auth handling from the example and the Flux TTS contract from the api skill.
If your integration uses a specific Deepgram SDK, install its skills for language-idiomatic patterns:
api — consolidated REST + WebSocket API referencerecipes — focused feature snippets (one feature, one language)starters — starter apps without third-party integrationsdocs — documentation findersetup-mcp — Deepgram MCP server installation