Skills

Skill 5 of 14

Docs

Find the right Deepgram documentation for any task. Use whenever someone needs help locating docs, understanding which API to use, or wants to ask questions about Deepgram.

2 minutes · 362 words · 12 sections

Install

$ npx skills add deepgram/skills --skill docs

$ npx skills add deepgram/skills

» /plugin marketplace add deepgram/skills

The first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.

Deepgram Documentation

Find the right docs for what you’re building with Deepgram.

Ask AI

Have a question? Get answers from Deepgram’s AI assistant at https://developers.deepgram.com/ask-ai (opens in a new tab).

Documentation by Topic

Speech-to-Text (STT)

Transcribe audio and video into text. Deepgram ships two actively maintained, next-gen model families — pick the one that matches your use case.

Nova (/v1/listen) — general-purpose transcription (captions, subtitles, batch files, live streams). Rich feature set including intelligence overlays (diarize, summarize, sentiment, topics, intents).
Flux STT (/v2/listen) — conversational-audio transcription for voice agents and interactive assistants. Built-in turn-taking (EOT events, mid-session reconfig).

Docs:

Text-to-Speech (TTS)

Convert text into natural-sounding speech. Deepgram ships two TTS model families on separate endpoints — the voices do not overlap.

Aura (/v1/speak) — the broadest voice catalog (English, Spanish, German, Dutch, French, Italian, Japanese) and compressed/containerized output. Use for one-shot synthesis and any non-English voice.
Flux TTS (/v2/speak) — streaming-first, voice-agent-first synthesis. Turn-based lifecycle, barge-in with spoken-text feedback, and prosody that carries across turns. English at launch.

Docs:

Voice Agent

Build conversational voice agents powered by Deepgram.

Text and Audio Intelligence

Analyze text and audio for sentiment, topics, intents, summaries, and more.

Audio Intelligence Docs (opens in a new tab)

Self-Hosted Deployments

Run Deepgram on your own infrastructure.

Self-Hosted Introduction (opens in a new tab)

API Reference

Full reference for all Deepgram REST and WebSocket APIs.

API Reference (opens in a new tab)

SDK-Specific Skills

For language-idiomatic code patterns (imports, async idioms, error handling, type shapes), install the Deepgram SDK’s own skills. Every Deepgram SDK publishes 7 product 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-dotnet-sdk     # C# / .NET

Swift and Kotlin SDK skills are not listed because those repositories are not public and npx skills add cannot reach them. For browser work, open the browser-agent skill: it covers the four Browser Agent SDK packages published on npm (@deepgram/agents, @deepgram/react, @deepgram/ui, @deepgram/agents-widget).

api: consolidated REST + WebSocket API reference
recipes: minimal runnable feature snippets per language
examples: full integration examples with third-party platforms
starters: runnable starter apps (framework × feature)
audio-intelligence: the /v1/listen analysis parameters
text-intelligence: POST /v1/read for text you already have
browser-agent: running a voice agent in a browser
cli: deepctl for shell and CI work
self-hosted: running Deepgram on your own GPUs
setup-mcp: Deepgram MCP server installation

MCP Server

For direct documentation querying from your AI coding tool, use the setup-mcp skill to install the Deepgram MCP server.

About this skill

Trigger

Find the right Deepgram documentation for any task. Use whenever someone needs help locating docs, understanding which API to use, or wants to ask questions about Deepgram. Covers all product areas: speech-to-text (Nova, Flux STT), text-to-speech (Aura, Flux TTS), voice agents, audio intelligence, and self-hosted deployments.

The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.

Colophon for this issue

Colophon

How this issue was made

Source

github.com/deepgram/skills, branch main, last pushed 20 September 2026.

Licence

Discovery

14 skills found by walking the repository tree for SKILL.md, not by matching a directory convention. One layout observed: skills/*/SKILL.md.

Issue colours

Resolved from a deterministic hash of the owner name. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Heading repairs

1 repair applied to this skill so the document has one h1 and no skipped levels:

Shifted “12 headings” from h1 to h2 so the skill title is the only h1.

Spec compliance

Every skill satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a skill come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Marketplace

A plugin manifest is published at .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.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /deepgram/skills.md, and each skill at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

Deepgram Documentation

Find the right docs for what you’re building with Deepgram.

Transcribe audio and video into text. Deepgram ships two actively maintained, next-gen model families — pick the one that matches your use case.

Nova (/v1/listen) — general-purpose transcription (captions, subtitles, batch files, live streams). Rich feature set including intelligence overlays (diarize, summarize, sentiment, topics, intents).

Flux STT (/v2/listen) — conversational-audio transcription for voice agents and interactive assistants. Built-in turn-taking (EOT events, mid-session reconfig).

Docs:

Convert text into natural-sounding speech. Deepgram ships two TTS model families on separate endpoints — the voices do not overlap.

Aura (/v1/speak) — the broadest voice catalog (English, Spanish, German, Dutch, French, Italian, Japanese) and compressed/containerized output. Use for one-shot synthesis and any non-English voice.

Flux TTS (/v2/speak) — streaming-first, voice-agent-first synthesis. Turn-based lifecycle, barge-in with spoken-text feedback, and prosody that carries across turns. English at launch.

Docs:

Build conversational voice agents powered by Deepgram.

Analyze text and audio for sentiment, topics, intents, summaries, and more.

Run Deepgram on your own infrastructure.

Full reference for all Deepgram REST and WebSocket APIs.

For language-idiomatic code patterns (imports, async idioms, error handling, type shapes), install the Deepgram SDK’s own skills. Every Deepgram SDK publishes 7 product 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-dotnet-sdk     # C# / .NET

api: consolidated REST + WebSocket API reference

recipes: minimal runnable feature snippets per language

examples: full integration examples with third-party platforms

starters: runnable starter apps (framework × feature)

audio-intelligence: the /v1/listen analysis parameters

text-intelligence: POST /v1/read for text you already have

browser-agent: running a voice agent in a browser

cli: deepctl for shell and CI work

self-hosted: running Deepgram on your own GPUs

setup-mcp: Deepgram MCP server installation

For direct documentation querying from your AI coding tool, use the setup-mcp skill to install the Deepgram MCP server.