DeepgramSTT

Use DeepgramSTT for production voice pipelines that need high accuracy, word-level timestamps, and wide language/model support via Deepgram’s V1 (Nova) streaming API.

Looking for eager end-of-turn / preflight signals? Use DeepgramFlux instead — it connects to Deepgram’s V2 API and supports the eager LLM pipeline.

Prerequisites

• A Deepgram API key
• The @deepgram/sdk peer dependency installed:

npm install @deepgram/sdk

For production, set up a proxy server so your API key stays server-side.

Basic setup

import { CompositeVoice, DeepgramSTT, AnthropicLLM, NativeTTS } from '@lukeocodes/composite-voice';

const agent = new CompositeVoice({
  stt: new DeepgramSTT({
    proxyUrl: '/api/proxy/deepgram',
    options: {
      model: 'nova-3',
      smartFormat: true,
    },
  }),
  llm: new AnthropicLLM({
    proxyUrl: '/api/proxy/anthropic',
    model: 'claude-haiku-4-5',
    systemPrompt: 'You are a helpful voice assistant. Keep responses brief.',
  }),
  tts: new NativeTTS(),
});

await agent.start();

Configuration options

See the API reference for the full list.

Models

DeepgramSTT uses Deepgram’s V1 (Nova) model family:

V1 uses an event-streaming model with Results events containing is_final and speech_final flags. Nova-3 delivers the best accuracy across the widest range of languages. Use Nova-2 variants for domain-specific vocabulary.

For Flux models (e.g., flux-general-en) with turn-based transcription and eager end-of-turn signals, use the DeepgramFlux provider instead.

Complete example

import { CompositeVoice, DeepgramSTT, AnthropicLLM, DeepgramTTS } from '@lukeocodes/composite-voice';

const agent = new CompositeVoice({
  stt: new DeepgramSTT({
    proxyUrl: '/api/proxy/deepgram',
    language: 'en',
    interimResults: true,
    options: {
      model: 'nova-3',
      smartFormat: true,
      punctuation: true,
      endpointing: 300,
      keywords: ['CompositeVoice'],
    },
  }),
  llm: new AnthropicLLM({
    proxyUrl: '/api/proxy/anthropic',
    model: 'claude-haiku-4-5',
    maxTokens: 256,
    systemPrompt: 'You are a helpful voice assistant. Keep responses under two sentences.',
  }),
  tts: new DeepgramTTS({
    proxyUrl: '/api/proxy/deepgram',
    voice: 'aura-2-thalia-en',
  }),
  // eagerLLM requires DeepgramFlux — see the DeepgramFlux guide for eager pipeline setup
  conversationHistory: { enabled: true, maxTurns: 10 },
  logging: { enabled: true, level: 'info' },
});

agent.on('transcription:final', (event) => {
  console.log('User said:', event.text);
});

await agent.start();

Tips and gotchas

• Always use a proxy in production. Pass proxyUrl instead of apiKey so your Deepgram key never reaches the browser. The SDK converts http(s) to ws(s) automatically.
• Install the peer dependency. DeepgramSTT dynamically imports @deepgram/sdk at initialization. If the package is missing, you get a clear error with install instructions.
• Utterance buffering. Deepgram may split one utterance into multiple is_final segments before emitting speech_final. DeepgramSTT buffers these segments and delivers the complete utterance text when speechFinal: true.
• No preflight signals. DeepgramSTT (V1/Nova) does not emit preflight/eager end-of-turn events. For the eager LLM pipeline, use DeepgramFlux instead.
• Connection timeout. The WebSocket connection defaults to a 10-second timeout. Adjust with timeout in the config if your network is slow.

Related resources

• Deepgram pipeline example — full Deepgram STT + TTS pipeline
• Eager pipeline example — preflight signals with speculative LLM (uses DeepgramFlux)
• Deepgram options example — explore transcription options
• DeepgramFlux guide — V2 Flux provider with eager end-of-turn signals
• Proxy server example — secure your API key server-side
• API reference: DeepgramSTT
• Providers reference