Deepgram STT

DeepgramSTT streams PCM (or mulaw / opus / flac) audio to Deepgram’s v1 /listen WebSocket endpoint. Uses the ws package — no vendor SDK required. Handles KeepAlive pings, Finalize / CloseStream graceful shutdown, and surfaces both Results transcripts and SpeechStarted / UtteranceEnd VAD events.

Install

deepgram ships in the base install.

npm install getpatter

Usage

Use the namespaced import (getpatter/stt/deepgram) or the flat re-export (DeepgramSTT). Both auto-resolve DEEPGRAM_API_KEY from the environment when apiKey is omitted.

// Namespaced import
import * as deepgram from "getpatter/stt/deepgram";

const stt = new deepgram.STT();                                    // reads DEEPGRAM_API_KEY
const stt2 = new deepgram.STT({ apiKey: "dg_...", model: "nova-3", language: "en" });

// Flat alias (equivalent)
import { DeepgramSTT } from "getpatter";

const stt3 = new DeepgramSTT();

# See python-sdk/providers/deepgram for the Python twin.

Plug it into an agent:

// npx tsx example.ts
import { Patter, Twilio, DeepgramSTT, ElevenLabsTTS } from "getpatter";

const phone = new Patter({ carrier: new Twilio(), phoneNumber: "+15550001234" });

const agent = phone.agent({
  stt: new DeepgramSTT(),                             // DEEPGRAM_API_KEY from env
  tts: new ElevenLabsTTS({ voiceId: "rachel" }),
  systemPrompt: "You are a helpful assistant.",
});

await phone.serve({ agent });

Models and rates

Deepgram bills per minute of streamed audio. Per-model rates (defaults from getpatter/pricing):

Model	Rate / min
`nova-3` (default)	$0.0077
`nova-3-multilingual`	$0.0092
`nova-2`	$0.0058
`nova`	$0.0043
`whisper-large`	$0.0048
`whisper-medium`	$0.0048

Override via new Patter({ pricing: { deepgram: { models: { "nova-2": { price: ... } } } } }).

Languages

language: "en" by default. Pass any Deepgram-supported BCP-47 code (e.g. "es", "fr", "de", "it"). For mixed-language calls use nova-3-multilingual.

Options

Option	Default	Notes
`apiKey`	—	Reads from `DEEPGRAM_API_KEY` when omitted.
`model`	`"nova-3"`	Any Deepgram model id.
`language`	`"en"`	BCP-47 code.
`encoding`	`"linear16"`	`"linear16"`, `"mulaw"`, `"alaw"`, `"opus"`, `"flac"`.
`sampleRate`	`16000`	8000, 16000, 24000, 44100, 48000 Hz.
`endpointingMs`	`150`	Silence (ms) before Deepgram closes a turn.
`utteranceEndMs`	`1000`	Server-side endpoint detection (min 1000).
`smartFormat`	`true`	Punctuation + numerals.
`interimResults`	`true`	Stream partial transcripts.
`vadEvents`	`true`	Emit `SpeechStarted` / `UtteranceEnd`.

Get Started

Setting up Patter

Observability

Integrations

Development

Deepgram STT

Deepgram STT

Install

Usage

Models and rates

Languages

Options

​Deepgram STT

​Install

​Usage

​Models and rates

​Languages

​Options

Deepgram STT

Install

Usage

Models and rates

Languages

Options