Labsco
deepgram logo

docs

★ 13

by deepgram · part of deepgram/skills

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, text-to-speech, voice agents, audio intelligence, and self-hosted deployments.

🔥🔥✓ VerifiedFreeAdvanced setup
#ai-image#voice#devops#git#video-editing
🧩 One of 7 skills in the deepgram/skills package — works on its own, and pairs well with its siblings.

This is the playbook your agent receives when the skill activates — you don't need to read it to use the skill, but it's here to audit before installing.

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.

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.

Self-Hosted Deployments

Run Deepgram on your own infrastructure.

API Reference

Full reference for all Deepgram REST and WebSocket APIs.

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 plus a maintainer skill:

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
npx skills add deepgram/deepgram-kotlin-sdk     # Kotlin
npx skills add deepgram/deepgram-dotnet-sdk     # C# / .NET
npx skills add deepgram/deepgram-browser-sdk    # Browser TypeScript
  • 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)
  • 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.