6 skills published from this repository. No description was given upstream, so this issue takes its voice from the chapters themselves.
6 chapters · 11 minutes · 2,442 words
npx skills add deepgram/skills/plugin marketplace add deepgram/skillsSkills are folders of instructions and resources that AI coding tools load to help you build with Deepgram faster. Each skill teaches your tool how to use a specific part of the Deepgram platform — from API reference to finding the right starter app.
For more information, check out:
This repository contains skills for building with Deepgram’s speech-to-text, text-to-speech, voice agent, and audio intelligence APIs. Skills are agent-agnostic — plain markdown that any AI coding tool can consume.
Deepgram ships two actively maintained, industry-leading speech-to-text model families:
/v1/listen) — general-purpose transcription with a rich intelligence feature set (diarize, summarize, sentiment, topics, intents). Use for captions, subtitles, batch, and general live streaming./v2/listen, model=flux-general-en) — conversational STT with built-in turn detection. Use for voice agents and interactive assistants. See the api skill for the full Nova vs Flux decision guide.Some skills are hand-written, others are generated from Deepgram’s OpenAPI (opens in a new tab) and AsyncAPI (opens in a new tab) specs.
| Skill | Description |
|---|---|
| api (opens in a new tab) | Full API reference for all Deepgram REST and WebSocket APIs, generated from OpenAPI and AsyncAPI specs |
| docs (opens in a new tab) | Find the right Deepgram documentation for any task |
| starters (opens in a new tab) | Clone a ready-to-run demo app in your language and start building — 13 frameworks, 7 features |
| recipes (opens in a new tab) | Focused runnable recipes for one feature × one language — minimal working code (< 50 lines) |
Each Deepgram SDK repository publishes its own set of language-idiomatic skills under .agents/skills/:
npx skills add deepgram/deepgram-python-sdk # Python
npx skills add deepgram/deepgram-js-sdk # JavaScript / TypeScript
npx skills add deepgram/deepgram-java-sdk # Java
npx skills add deepgram/deepgram-go-sdk # Go
npx skills add deepgram/deepgram-rust-sdk # Rust
npx skills add deepgram/deepgram-swift-sdk # Swift
Each SDK ships 7 product skills named deepgram-{lang}-{product} plus a maintainer skill deepgram-{lang}-maintaining-sdk. Example names for the Python SDK:
deepgram-python-speech-to-textdeepgram-python-text-to-speechdeepgram-python-text-intelligencedeepgram-python-audio-intelligencedeepgram-python-voice-agentdeepgram-python-conversational-sttdeepgram-python-management-apideepgram-python-maintaining-sdkThe deepgram-{lang}- prefix keeps names globally unique so installing skills from multiple SDKs never overwrites another SDK’s skills.
This deepgram/skills repo covers product contracts (API reference, docs, starters, recipes, integrations, MCP). The SDK repos cover language-specific usage.
Works with Claude Code, Cursor, Windsurf, GitHub Copilot, Gemini CLI, and 30+ others (opens in a new tab):
npx skills add deepgram/skillsRegister this repository as a plugin marketplace:
/plugin marketplace add deepgram/skillsThen install the Deepgram plugin:
/plugin install deepgram@deepgram-agent-skillsThis gives you the following slash commands:
/deepgram:api — Deepgram API reference/deepgram:docs — Find the right documentation/deepgram:starters — Clone a starter app/deepgram:recipes — Focused runnable recipes for one feature × one language/deepgram:examples — Integration examples with third-party platforms/deepgram:setup-mcp — Set up the Deepgram MCP serverYou can also install SDK-specific skill plugins from the same marketplace:
/plugin install deepgram-js-sdk@deepgram-agent-skills
/plugin install deepgram-python-sdk@deepgram-agent-skills
/plugin install deepgram-java-sdk@deepgram-agent-skills
/plugin install deepgram-go-sdk@deepgram-agent-skills
/plugin install deepgram-rust-sdk@deepgram-agent-skills
/plugin install deepgram-dotnet-sdk@deepgram-agent-skillsEach SDK plugin installs the 7 language-idiomatic skills from that SDK’s repository.
Skills are a folder with a SKILL.md file containing YAML frontmatter and instructions. Use the template (opens in a new tab) as a starting point:
---
name: my-skill-name
description: A clear description of what this skill does and when to use it.
---
# My Skill Name
[Instructions that your AI tool will follow when this skill is active]The frontmatter requires two fields:
name — A unique identifier for your skill (lowercase, hyphens for spaces)description — What the skill does and when to use itThe API reference skills are generated from Deepgram’s specs. To regenerate:
# Fetch the latest specs
bun run scripts/fetch-specs.ts https://dpgr.am/openapi.yml https://dpgr.am/asyncapi.yml
# Generate reference markdown
bun install && bun run scripts/generate-skills.tsmain, last pushed 1 May 2026.SKILL.md, not by matching a directory convention. One layout observed: skills/*/SKILL.md.h1 and no skipped levels:.claude-plugin/marketplace.json by Deepgram Developer Relations, declaring 7 plugins. It is read for editorial metadata only — never as the skill index, which is always the repository tree./deepgram/skills.md, and each chapter at its own .md URL.| Integration examples with third-party platforms (Twilio, LiveKit, LangChain, Vercel AI SDK, etc.) |
| setup-mcp (opens in a new tab) | Set up the Deepgram MCP server for querying docs directly from your AI coding tool |