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
Related Deepgram skills
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.
1---
2name: docs
3description: >
4 Find the right Deepgram documentation for any task. Use whenever someone needs help locating
5 docs, understanding which API to use, or wants to ask questions about Deepgram. Covers all
6 product areas: speech-to-text (Nova, Flux STT), text-to-speech (Aura, Flux TTS), voice agents,
7 audio intelligence, and self-hosted deployments.
8metadata:
9 source: https://skillmd.com/skills/deepgram/docs
10---
11
12# Deepgram Documentation
13
14Find the right docs for what you're building with Deepgram.
15
16## Ask AI
17
18Have a question? Get answers from Deepgram's AI assistant at <https://developers.deepgram.com/ask-ai>.
19
20## Documentation by Topic
21
22### Speech-to-Text (STT)
23
24Transcribe audio and video into text. Deepgram ships two actively maintained, next-gen model families — pick the one that matches your use case.
25
26- **Nova** (`/v1/listen`) — general-purpose transcription (captions, subtitles, batch files, live streams). Rich feature set including intelligence overlays (diarize, summarize, sentiment, topics, intents).
27- **Flux STT** (`/v2/listen`) — conversational-audio transcription for voice agents and interactive assistants. Built-in turn-taking (EOT events, mid-session reconfig).
28
29Docs:
30- [STT Getting Started (Nova)](https://developers.deepgram.com/docs/stt/getting-started)
31- [Flux STT Quickstart](https://developers.deepgram.com/docs/flux/quickstart)
32- [Nova 3 → Flux STT migration](https://developers.deepgram.com/docs/flux/nova-3-migration)
33- [Flux STT language prompting](https://developers.deepgram.com/docs/flux/language-prompting)
34
35### Text-to-Speech (TTS)
36
37Convert text into natural-sounding speech. Deepgram ships two TTS model families on separate endpoints — the voices do not overlap.
38
39- **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.
40- **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.
41
42Docs:
43- [Text-to-Speech Docs (Aura)](https://developers.deepgram.com/docs/tts-rest)
44- [Aura voices and languages](https://developers.deepgram.com/docs/tts-models)
45- [Flux TTS Overview](https://developers.deepgram.com/docs/flux-tts/overview)
46- [Flux TTS Streaming Quickstart](https://developers.deepgram.com/docs/flux-tts/quickstart)
47- [Flux TTS Batch (REST) Quickstart](https://developers.deepgram.com/docs/flux-tts/batch)
48- [Flux TTS batch vs streaming](https://developers.deepgram.com/docs/flux-tts/batch-vs-streaming)
49- [Flux TTS voices](https://developers.deepgram.com/docs/flux-tts/voices)
50- [Aura → Flux TTS migration](https://developers.deepgram.com/docs/flux-tts/migrating)
51
52### Voice Agent
53
54Build conversational voice agents powered by Deepgram.
55
56- [Voice Agent Docs](https://developers.deepgram.com/docs/voice-agent)
57- [Voice Agent TTS models (Aura vs Flux TTS)](https://developers.deepgram.com/docs/voice-agent-tts-models)
58- [Build a Flux TTS voice agent](https://developers.deepgram.com/docs/flux-tts/voice-agent)
59
60### Text and Audio Intelligence
61
62Analyze text and audio for sentiment, topics, intents, summaries, and more.
63
64- [Audio Intelligence Docs](https://developers.deepgram.com/docs/audio-intelligence)
65
66### Self-Hosted Deployments
67
68Run Deepgram on your own infrastructure.
69
70- [Self-Hosted Introduction](https://developers.deepgram.com/docs/self-hosted-introduction)
71
72### API Reference
73
74Full reference for all Deepgram REST and WebSocket APIs.
75
76- [API Reference](https://developers.deepgram.com/reference/deepgram-api-overview)
77
78## SDK-Specific Skills
79
80For 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:
81
82```bash
83npx skills add deepgram/deepgram-python-sdk # Python
84npx skills add deepgram/deepgram-js-sdk # JavaScript / TypeScript
85npx skills add deepgram/deepgram-java-sdk # Java
86npx skills add deepgram/deepgram-go-sdk # Go
87npx skills add deepgram/deepgram-rust-sdk # Rust
88npx skills add deepgram/deepgram-swift-sdk # Swift
89npx skills add deepgram/deepgram-kotlin-sdk # Kotlin
90npx skills add deepgram/deepgram-dotnet-sdk # C# / .NET
91npx skills add deepgram/deepgram-browser-sdk # Browser TypeScript
92```
93
94## Related Deepgram skills
95
96- `api` — consolidated REST + WebSocket API reference
97- `recipes` — minimal runnable feature snippets per language
98- `examples` — full integration examples with third-party platforms
99- `starters` — runnable starter apps (framework × feature)
100- `setup-mcp` — Deepgram MCP server installation
101
102## MCP Server
103
104For direct documentation querying from your AI coding tool, use the `setup-mcp` skill to install the Deepgram MCP server.